{"url":"/task/domain-adaptation","name":"Domain Adaptation","slug":"domain-adaptation","description_markdown":"**Domain Adaptation** is the task of adapting models across domains. This is motivated by the challenge where the test and training datasets fall from different data distributions due to some factor. Domain adaptation aims to build machine learning models that can be generalized into a target domain and dealing with the discrepancy across domain distributions. \r\n\r\nFurther readings:\r\n\r\n- [A Brief Review of Domain Adaptation](https://paperswithcode.com/paper/a-brief-review-of-domain-adaptation)\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Unsupervised Image-to-Image Translation Networks](https://arxiv.org/pdf/1703.00848v6.pdf) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":6439,"papers_with_code":2400,"benchmarks":58,"benchmark_tables_in_archive":58,"benchmark_tables_shown":58,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":96,"subtasks":13,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/domain-adaptation-on-office-31","slug":"domain-adaptation-on-office-31","dataset":"Office-31","dataset_url":"/dataset/office-31","rows_in_archive":40,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"FFTAT","paper_title":"Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation","paper_url":"/paper/feature-fusion-transferability-aware","paper_date":"2024-11-10","arxiv_id":"2411.07794","code_links":[{"title":"Shawey94/NoisyNN","url":"https://github.com/Shawey94/NoisyNN"},{"title":"Shawey94/WACV2025-FFTAT","url":"https://github.com/Shawey94/WACV2025-FFTAT"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-synthia-to-cityscapes","slug":"domain-adaptation-on-synthia-to-cityscapes","dataset":"SYNTHIA-to-Cityscapes","dataset_url":"/dataset/synthia","rows_in_archive":33,"metrics":["mIoU","Extra Manual Annotation"],"first_row_in_archive_order":{"model":"HALO","paper_title":"Hyperbolic Active Learning for Semantic Segmentation under Domain Shift","paper_url":"/paper/hyperbolic-active-learning-for-semantic","paper_date":"2023-06-19","arxiv_id":"2306.11180","code_links":[{"title":"paolomandica/HALO","url":"https://github.com/paolomandica/HALO"}],"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-adaptation-on-office-home","slug":"domain-adaptation-on-office-home","dataset":"Office-Home","dataset_url":"/dataset/office-home","rows_in_archive":29,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SWG","paper_title":"Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance","paper_url":"/paper/combining-inherent-knowledge-of-vision","paper_date":"2023-12-07","arxiv_id":"2312.04066","code_links":[{"title":"ThomasWestfechtel/SWG","url":"https://github.com/ThomasWestfechtel/SWG"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-gta5-to-cityscapes","slug":"domain-adaptation-on-gta5-to-cityscapes","dataset":"GTA5 to Cityscapes","dataset_url":"/dataset/gta5","rows_in_archive":28,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"HALO","paper_title":"Hyperbolic Active Learning for Semantic Segmentation under Domain Shift","paper_url":"/paper/hyperbolic-active-learning-for-semantic","paper_date":"2023-06-19","arxiv_id":"2306.11180","code_links":[{"title":"paolomandica/HALO","url":"https://github.com/paolomandica/HALO"}],"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-adaptation-on-visda2017","slug":"domain-adaptation-on-visda2017","dataset":"VisDA2017","dataset_url":"/dataset/visda-2017","rows_in_archive":28,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"FFTAT","paper_title":"Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation","paper_url":"/paper/feature-fusion-transferability-aware","paper_date":"2024-11-10","arxiv_id":"2411.07794","code_links":[{"title":"Shawey94/NoisyNN","url":"https://github.com/Shawey94/NoisyNN"},{"title":"Shawey94/WACV2025-FFTAT","url":"https://github.com/Shawey94/WACV2025-FFTAT"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-imageclef-da","slug":"domain-adaptation-on-imageclef-da","dataset":"ImageCLEF-DA","dataset_url":"/dataset/imageclef-da","rows_in_archive":17,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CMKD","paper_title":"Unsupervised Domain Adaption Harnessing Vision-Language Pre-training","paper_url":"/paper/unsupervised-domain-adaption-harnessing","paper_date":"2024-04-19","arxiv_id":null,"code_links":[{"title":"Wenlve-Zhou/VLP-UDA","url":"https://github.com/Wenlve-Zhou/VLP-UDA"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-cityscapes-to-acdc","slug":"domain-adaptation-on-cityscapes-to-acdc","dataset":"Cityscapes to ACDC","dataset_url":"/dataset/acdc-adverse-conditions-dataset-with","rows_in_archive":16,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"SoRA","paper_title":"SoRA: Singular Value Decomposed Low-Rank Adaptation for Domain Generalizable Representation Learning","paper_url":"/paper/sora-singular-value-decomposed-low-rank","paper_date":"2024-12-05","arxiv_id":"2412.04077","code_links":[{"title":"ysj9909/DG-SoRA","url":"https://github.com/ysj9909/DG-SoRA"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-mnist-to-usps","slug":"domain-adaptation-on-mnist-to-usps","dataset":"MNIST-to-USPS","dataset_url":"/dataset/mnist","rows_in_archive":14,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"FACT","paper_title":"FACT: Federated Adversarial Cross Training","paper_url":"/paper/fact-federated-adversarial-cross-training","paper_date":"2023-06-01","arxiv_id":"2306.00607","code_links":[{"title":"jonas-lippl/fact","url":"https://github.com/jonas-lippl/fact"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-svhn-to-mnist","slug":"domain-adaptation-on-svhn-to-mnist","dataset":"SVHN-to-MNIST","dataset_url":"/dataset/svhn","rows_in_archive":14,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Mean teacher","paper_title":"Self-ensembling for visual domain adaptation","paper_url":"/paper/self-ensembling-for-visual-domain-adaptation","paper_date":"2017-06-16","arxiv_id":"1706.05208","code_links":[{"title":"thuml/Transfer-Learning-Library","url":"https://github.com/thuml/Transfer-Learning-Library"},{"title":"domainadaptation/salad","url":"https://github.com/domainadaptation/salad"},{"title":"Britefury/self-ensemble-visual-domain-adapt","url":"https://github.com/Britefury/self-ensemble-visual-domain-adapt"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-usps-to-mnist","slug":"domain-adaptation-on-usps-to-mnist","dataset":"USPS-to-MNIST","dataset_url":"/dataset/mnist","rows_in_archive":14,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"FAMCD","paper_title":"Unsupervised domain adaptation using feature aligned maximum classifier discrepancy","paper_url":"/paper/unsupervised-domain-adaptation-using-feature-2","paper_date":"2022-10-03","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-svnh-to-mnist","slug":"domain-adaptation-on-svnh-to-mnist","dataset":"SVNH-to-MNIST","dataset_url":"/dataset/mnist","rows_in_archive":9,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SRDA (RAN)","paper_title":"Learning Smooth Representation for Unsupervised Domain Adaptation","paper_url":"/paper/190510748","paper_date":"2019-05-26","arxiv_id":"1905.10748","code_links":[{"title":"CuthbertCai/SRDA","url":"https://github.com/CuthbertCai/SRDA"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-molane","slug":"domain-adaptation-on-molane","dataset":"MoLane","dataset_url":"/dataset/carlane-benchmark","rows_in_archive":8,"metrics":["Lane Accuracy (LA)"],"first_row_in_archive_order":{"model":"UFLD-SGPCS-ResNet18","paper_title":"CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains","paper_url":"/paper/carlane-a-lane-detection-benchmark-for","paper_date":"2022-06-16","arxiv_id":"2206.08083","code_links":[{"title":"juliangebele/CARLANE","url":"https://github.com/juliangebele/CARLANE"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-mulane","slug":"domain-adaptation-on-mulane","dataset":"MuLane","dataset_url":"/dataset/carlane-benchmark","rows_in_archive":8,"metrics":["Lane Accuracy (LA)"],"first_row_in_archive_order":{"model":"UFLD-SGADA-ResNet32","paper_title":"CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains","paper_url":"/paper/carlane-a-lane-detection-benchmark-for","paper_date":"2022-06-16","arxiv_id":"2206.08083","code_links":[{"title":"juliangebele/CARLANE","url":"https://github.com/juliangebele/CARLANE"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-office-caltech","slug":"domain-adaptation-on-office-caltech","dataset":"Office-Caltech","dataset_url":null,"rows_in_archive":8,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"SPL","paper_title":"Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling","paper_url":"/paper/unsupervised-domain-adaptation-via-structured","paper_date":"2019-11-18","arxiv_id":"1911.07982","code_links":[{"title":"hellowangqian/domain-adaptation-capls","url":"https://github.com/hellowangqian/domain-adaptation-capls"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-tulane","slug":"domain-adaptation-on-tulane","dataset":"TuLane","dataset_url":"/dataset/carlane-benchmark","rows_in_archive":8,"metrics":["Lane Accuracy (LA)"],"first_row_in_archive_order":{"model":"UFLD-SGPCS-ResNet32","paper_title":"CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains","paper_url":"/paper/carlane-a-lane-detection-benchmark-for","paper_date":"2022-06-16","arxiv_id":"2206.08083","code_links":[{"title":"juliangebele/CARLANE","url":"https://github.com/juliangebele/CARLANE"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-cityscapes-to","slug":"domain-adaptation-on-cityscapes-to","dataset":"Cityscapes-to-FoggyZurich","dataset_url":null,"rows_in_archive":6,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CoDA","paper_title":"CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning","paper_url":"/paper/coda-instructive-chain-of-domain-adaptation","paper_date":"2024-03-26","arxiv_id":"2403.17369","code_links":[{"title":"Cuzyoung/CoDA","url":"https://github.com/Cuzyoung/CoDA"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-gtav-synscapes-to","slug":"domain-adaptation-on-gtav-synscapes-to","dataset":"GTAV+Synscapes to Cityscapes","dataset_url":null,"rows_in_archive":6,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"DDB","paper_title":"Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation","paper_url":"/paper/deliberated-domain-bridging-for-domain","paper_date":"2022-09-16","arxiv_id":"2209.07695","code_links":[{"title":"xiaoachen98/DDB","url":"https://github.com/xiaoachen98/DDB"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-synsig-to-gtsrb","slug":"domain-adaptation-on-synsig-to-gtsrb","dataset":"SYNSIG-to-GTSRB","dataset_url":"/dataset/gtsrb","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DFA-MCD","paper_title":"Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment","paper_url":"/paper/discriminative-feature-alignment","paper_date":"2020-06-23","arxiv_id":"2006.12770","code_links":[{"title":"JingWang18/Discriminative-Feature-Alignment","url":"https://github.com/JingWang18/Discriminative-Feature-Alignment"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-adaptation-on-cityscapes-to-1","slug":"domain-adaptation-on-cityscapes-to-1","dataset":"Cityscapes-to-FoggyDriving","dataset_url":null,"rows_in_archive":5,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"CoDA","paper_title":"CoDA: Instructive Chain-of-Domain Adaptation with Severity-Aware Visual Prompt Tuning","paper_url":"/paper/coda-instructive-chain-of-domain-adaptation","paper_date":"2024-03-26","arxiv_id":"2403.17369","code_links":[{"title":"Cuzyoung/CoDA","url":"https://github.com/Cuzyoung/CoDA"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-gta5-synscapes-to","slug":"domain-adaptation-on-gta5-synscapes-to","dataset":"GTA5+Synscapes to Cityscapes","dataset_url":"/dataset/gta5","rows_in_archive":5,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"MSCL","paper_title":"Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation","paper_url":"/paper/multi-source-domain-adaptation-with","paper_date":"2021-03-08","arxiv_id":"2103.04717","code_links":[],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-hmdbfull-to-ucf","slug":"domain-adaptation-on-hmdbfull-to-ucf","dataset":"HMDBfull-to-UCF","dataset_url":null,"rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"UNITE","paper_title":"Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training","paper_url":"/paper/unsupervised-video-domain-adaptation-with","paper_date":"2023-12-05","arxiv_id":"2312.02914","code_links":[{"title":"reddyav1/unite","url":"https://github.com/reddyav1/unite"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-mnist-to-mnist-m","slug":"domain-adaptation-on-mnist-to-mnist-m","dataset":"MNIST-to-MNIST-M","dataset_url":"/dataset/mnist-m","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DRANet","paper_title":"DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation","paper_url":"/paper/dranet-disentangling-representation-and","paper_date":"2021-03-24","arxiv_id":"2103.13447","code_links":[{"title":"Seung-Hun-Lee/DRANet","url":"https://github.com/Seung-Hun-Lee/DRANet"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/domain-adaptation-on-panoptic-synthia-to","slug":"domain-adaptation-on-panoptic-synthia-to","dataset":"Panoptic SYNTHIA-to-Cityscapes","dataset_url":null,"rows_in_archive":5,"metrics":["mPQ"],"first_row_in_archive_order":{"model":"MC-PanDA","paper_title":"MC-PanDA: Mask Confidence for Panoptic Domain Adaptation","paper_url":"/paper/mc-panda-mask-confidence-for-panoptic-domain","paper_date":"2024-07-19","arxiv_id":"2407.14110","code_links":[{"title":"helen1c/mc-panda","url":"https://github.com/helen1c/mc-panda"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-panoptic-synthia-to-1","slug":"domain-adaptation-on-panoptic-synthia-to-1","dataset":"Panoptic SYNTHIA-to-Mapillary","dataset_url":null,"rows_in_archive":5,"metrics":["mPQ"],"first_row_in_archive_order":{"model":"MC-PanDA","paper_title":"MC-PanDA: Mask Confidence for Panoptic Domain Adaptation","paper_url":"/paper/mc-panda-mask-confidence-for-panoptic-domain","paper_date":"2024-07-19","arxiv_id":"2407.14110","code_links":[{"title":"helen1c/mc-panda","url":"https://github.com/helen1c/mc-panda"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-ucf-hmdb-full","slug":"domain-adaptation-on-ucf-hmdb-full","dataset":"UCF --> HMDB (full)","dataset_url":null,"rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"UNITE","paper_title":"Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training","paper_url":"/paper/unsupervised-video-domain-adaptation-with","paper_date":"2023-12-05","arxiv_id":"2312.02914","code_links":[{"title":"reddyav1/unite","url":"https://github.com/reddyav1/unite"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-ucf-to-hmdbfull","slug":"domain-adaptation-on-ucf-to-hmdbfull","dataset":"UCF-to-HMDBfull","dataset_url":null,"rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"UNITE","paper_title":"Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training","paper_url":"/paper/unsupervised-video-domain-adaptation-with","paper_date":"2023-12-05","arxiv_id":"2312.02914","code_links":[{"title":"reddyav1/unite","url":"https://github.com/reddyav1/unite"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-domainnet-1","slug":"domain-adaptation-on-domainnet-1","dataset":"DomainNet","dataset_url":"/dataset/domainnet","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SPM","paper_title":"Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation","paper_url":"/paper/shuffle-patchmix-augmentation-with-confidence","paper_date":"2025-05-30","arxiv_id":"2505.24216","code_links":[{"title":"PrasannaPulakurthi/SPM","url":"https://github.com/PrasannaPulakurthi/SPM"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-gtav-to-cityscapes-1","slug":"domain-adaptation-on-gtav-to-cityscapes-1","dataset":"GTAV to Cityscapes+Mapillary","dataset_url":null,"rows_in_archive":4,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"Rein","paper_title":"Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation","paper_url":"/paper/stronger-fewer-superior-harnessing-vision","paper_date":"2023-12-07","arxiv_id":"2312.04265","code_links":[{"title":"w1oves/rein","url":"https://github.com/w1oves/rein"},{"title":"cuzyoung/crossearth","url":"https://github.com/cuzyoung/crossearth"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-hmdb-ucf-full","slug":"domain-adaptation-on-hmdb-ucf-full","dataset":"HMDB --> UCF (full)","dataset_url":null,"rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TranSVAE","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-synth-digits-to-svhn","slug":"domain-adaptation-on-synth-digits-to-svhn","dataset":"Synth Digits-to-SVHN","dataset_url":null,"rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DSN (DANN)","paper_title":"Domain Separation Networks","paper_url":"/paper/domain-separation-networks","paper_date":"2016-08-22","arxiv_id":"1608.06019","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/domain_adaptation"},{"title":"fungtion/DSN","url":"https://github.com/fungtion/DSN"},{"title":"AmirHussein96/Simplified-DSN","url":"https://github.com/AmirHussein96/Simplified-DSN"},{"title":"WinChua/CDRTR","url":"https://github.com/WinChua/CDRTR"},{"title":"better-chao/DSN","url":"https://github.com/better-chao/DSN"}],"syntology":{"n":14,"n_ran":5,"n_unverified":9,"n_pointer_only":6}}},{"leaderboard":"/sota/domain-adaptation-on-synth-signs-to-gtsrb","slug":"domain-adaptation-on-synth-signs-to-gtsrb","dataset":"Synth Signs-to-GTSRB","dataset_url":"/dataset/gtsrb","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Mean teacher","paper_title":"Self-ensembling for visual domain adaptation","paper_url":"/paper/self-ensembling-for-visual-domain-adaptation","paper_date":"2017-06-16","arxiv_id":"1706.05208","code_links":[{"title":"thuml/Transfer-Learning-Library","url":"https://github.com/thuml/Transfer-Learning-Library"},{"title":"domainadaptation/salad","url":"https://github.com/domainadaptation/salad"},{"title":"Britefury/self-ensemble-visual-domain-adapt","url":"https://github.com/Britefury/self-ensemble-visual-domain-adapt"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-hmdbsmall-to-ucf","slug":"domain-adaptation-on-hmdbsmall-to-ucf","dataset":"HMDBsmall-to-UCF","dataset_url":null,"rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TA3N","paper_title":"Temporal Attentive Alignment for Video Domain Adaptation","paper_url":"/paper/temporal-attentive-alignment-for-video-domain","paper_date":"2019-05-26","arxiv_id":"1905.10861","code_links":[{"title":"cmhungsteve/TA3N","url":"https://github.com/cmhungsteve/TA3N"},{"title":"olivesgatech/TA3N","url":"https://github.com/olivesgatech/TA3N"},{"title":"jonmun/EPIC-KITCHENS-100_UDA_TA3N","url":"https://github.com/jonmun/EPIC-KITCHENS-100_UDA_TA3N"},{"title":"mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation","url":"https://github.com/mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation"},{"title":"mustafa1728/TA3N-Lightning","url":"https://github.com/mustafa1728/TA3N-Lightning"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-olympic-to-hmdbsmall","slug":"domain-adaptation-on-olympic-to-hmdbsmall","dataset":"Olympic-to-HMDBsmall","dataset_url":null,"rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TA3N","paper_title":"Temporal Attentive Alignment for Video Domain Adaptation","paper_url":"/paper/temporal-attentive-alignment-for-video-domain","paper_date":"2019-05-26","arxiv_id":"1905.10861","code_links":[{"title":"cmhungsteve/TA3N","url":"https://github.com/cmhungsteve/TA3N"},{"title":"olivesgatech/TA3N","url":"https://github.com/olivesgatech/TA3N"},{"title":"jonmun/EPIC-KITCHENS-100_UDA_TA3N","url":"https://github.com/jonmun/EPIC-KITCHENS-100_UDA_TA3N"},{"title":"mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation","url":"https://github.com/mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation"},{"title":"mustafa1728/TA3N-Lightning","url":"https://github.com/mustafa1728/TA3N-Lightning"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-synscapes-to-cityscapes","slug":"domain-adaptation-on-synscapes-to-cityscapes","dataset":"Synscapes-to-Cityscapes","dataset_url":"/dataset/synscapes","rows_in_archive":3,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"ProDA+CRA","paper_title":"Cross-Region Domain Adaptation for Class-level Alignment","paper_url":"/paper/cross-region-domain-adaptation-for-class","paper_date":"2021-09-14","arxiv_id":"2109.06422","code_links":[],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-ucf-to-hmdbsmall","slug":"domain-adaptation-on-ucf-to-hmdbsmall","dataset":"UCF-to-HMDBsmall","dataset_url":null,"rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TA3N","paper_title":"Temporal Attentive Alignment for Video Domain Adaptation","paper_url":"/paper/temporal-attentive-alignment-for-video-domain","paper_date":"2019-05-26","arxiv_id":"1905.10861","code_links":[{"title":"cmhungsteve/TA3N","url":"https://github.com/cmhungsteve/TA3N"},{"title":"olivesgatech/TA3N","url":"https://github.com/olivesgatech/TA3N"},{"title":"jonmun/EPIC-KITCHENS-100_UDA_TA3N","url":"https://github.com/jonmun/EPIC-KITCHENS-100_UDA_TA3N"},{"title":"mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation","url":"https://github.com/mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation"},{"title":"mustafa1728/TA3N-Lightning","url":"https://github.com/mustafa1728/TA3N-Lightning"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-ucf-to-olympic","slug":"domain-adaptation-on-ucf-to-olympic","dataset":"UCF-to-Olympic","dataset_url":null,"rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"TA3N","paper_title":"Temporal Attentive Alignment for Video Domain Adaptation","paper_url":"/paper/temporal-attentive-alignment-for-video-domain","paper_date":"2019-05-26","arxiv_id":"1905.10861","code_links":[{"title":"cmhungsteve/TA3N","url":"https://github.com/cmhungsteve/TA3N"},{"title":"olivesgatech/TA3N","url":"https://github.com/olivesgatech/TA3N"},{"title":"jonmun/EPIC-KITCHENS-100_UDA_TA3N","url":"https://github.com/jonmun/EPIC-KITCHENS-100_UDA_TA3N"},{"title":"mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation","url":"https://github.com/mustafa1728/TA3N-Lightning-Kitchen_Domain_Adaptation"},{"title":"mustafa1728/TA3N-Lightning","url":"https://github.com/mustafa1728/TA3N-Lightning"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-comic2k","slug":"domain-adaptation-on-comic2k","dataset":"Comic2k","dataset_url":"/dataset/comic2k","rows_in_archive":2,"metrics":[" mAP"],"first_row_in_archive_order":{"model":"DDT","paper_title":"Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detector","paper_url":"/paper/diffusion-domain-teacher-diffusion-guided","paper_date":"2025-06-04","arxiv_id":"2506.04211","code_links":[{"title":"heboyong/Diffusion-Domain-Teacher","url":"https://github.com/heboyong/Diffusion-Domain-Teacher"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-rotating-mnist","slug":"domain-adaptation-on-rotating-mnist","dataset":"Rotating MNIST","dataset_url":"/dataset/mnist","rows_in_archive":2,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"PCIDA","paper_title":"Continuously Indexed Domain Adaptation","paper_url":"/paper/continuously-indexed-domain-adaptation","paper_date":"2020-07-03","arxiv_id":"2007.01807","code_links":[{"title":"hehaodele/CIDA","url":"https://github.com/hehaodele/CIDA"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-canon-raw-low-light","slug":"domain-adaptation-on-canon-raw-low-light","dataset":"Canon RAW Low Light","dataset_url":"/dataset/canon-raw-low-light","rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"FSDA-LL Sony -> Canon","paper_title":"Few-Shot Domain Adaptation for Low Light RAW Image Enhancement","paper_url":"/paper/few-shot-domain-adaptation-for-low-light-raw","paper_date":"2023-03-27","arxiv_id":"2303.15528","code_links":[{"title":"Vishal-V/FSDA-LowLight","url":"https://github.com/Vishal-V/FSDA-LowLight"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-adaptation-on-foggy-cityscapes","slug":"domain-adaptation-on-foggy-cityscapes","dataset":"Foggy Cityscapes","dataset_url":"/dataset/foggy-cityscapes","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MILA","paper_title":"MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection","paper_url":"/paper/mila-memory-based-instance-level-adaptation-1","paper_date":"2023-11-20","arxiv_id":"2309.01086","code_links":[{"title":"hitachi-rd-cv/MILA","url":"https://github.com/hitachi-rd-cv/MILA"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-gta-to-foggycityscapes","slug":"domain-adaptation-on-gta-to-foggycityscapes","dataset":"GTA-to-FoggyCityscapes","dataset_url":null,"rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"FogAdapt+","paper_title":"FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images","paper_url":"/paper/leveraging-scale-invariance-and-uncertainity","paper_date":"2022-01-07","arxiv_id":"2201.02588","code_links":[],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-leukemiaattri","slug":"domain-adaptation-on-leukemiaattri","dataset":"LeukemiaAttri","dataset_url":"/dataset/leukemiaattri","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"ConfMix [23] L_100x_C2","paper_title":"A Large-scale Multi Domain Leukemia Dataset for the White Blood Cells Detection with Morphological Attributes for Explainability","paper_url":"/paper/a-large-scale-multi-domain-leukemia-dataset","paper_date":"2024-05-17","arxiv_id":"2405.10803","code_links":[{"title":"intelligentMachines-ITU/Blood-Cancer-Dataset-Lukemia-Attri-MICCAI-2024","url":"https://github.com/intelligentMachines-ITU/Blood-Cancer-Dataset-Lukemia-Attri-MICCAI-2024"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-mnist-m-to-mnist","slug":"domain-adaptation-on-mnist-m-to-mnist","dataset":"MNIST-M-to-MNIST","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DRANet","paper_title":"DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation","paper_url":"/paper/dranet-disentangling-representation-and","paper_date":"2021-03-24","arxiv_id":"2103.13447","code_links":[{"title":"Seung-Hun-Lee/DRANet","url":"https://github.com/Seung-Hun-Lee/DRANet"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/domain-adaptation-on-msda","slug":"domain-adaptation-on-msda","dataset":"MSDA","dataset_url":"/dataset/msda","rows_in_archive":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"MetaSelf-Learning","paper_title":"Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark","paper_url":"/paper/meta-self-learning-for-multi-source-domain","paper_date":"2021-08-24","arxiv_id":"2108.10840","code_links":[{"title":"bupt-ai-cz/Meta-SelfLearning","url":"https://github.com/bupt-ai-cz/Meta-SelfLearning"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-nikon-raw-low-light","slug":"domain-adaptation-on-nikon-raw-low-light","dataset":"Nikon RAW Low Light","dataset_url":"/dataset/nikon-camera-low-light-raw-image-dataset","rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"FSDA-LL Sony -> Nikon","paper_title":"Few-Shot Domain Adaptation for Low Light RAW Image Enhancement","paper_url":"/paper/few-shot-domain-adaptation-for-low-light-raw","paper_date":"2023-03-27","arxiv_id":"2303.15528","code_links":[{"title":"Vishal-V/FSDA-LowLight","url":"https://github.com/Vishal-V/FSDA-LowLight"}],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-adaptation-on-noisy-amazon-20","slug":"domain-adaptation-on-noisy-amazon-20","dataset":"Noisy-Amazon (20%)","dataset_url":"/dataset/amazon-product-data","rows_in_archive":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Butterfly","paper_title":"Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation","paper_url":"/paper/butterfly-robust-one-step-approach-towards","paper_date":"2019-05-19","arxiv_id":"1905.07720","code_links":[{"title":"fengliu90/Butterfly","url":"https://github.com/fengliu90/Butterfly"}],"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-adaptation-on-noisy-amazon-45","slug":"domain-adaptation-on-noisy-amazon-45","dataset":"Noisy-Amazon (45%)","dataset_url":"/dataset/amazon-product-data","rows_in_archive":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Butterfly","paper_title":"Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation","paper_url":"/paper/butterfly-robust-one-step-approach-towards","paper_date":"2019-05-19","arxiv_id":"1905.07720","code_links":[{"title":"fengliu90/Butterfly","url":"https://github.com/fengliu90/Butterfly"}],"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-adaptation-on-noisy-mnist-to-synd","slug":"domain-adaptation-on-noisy-mnist-to-synd","dataset":"Noisy-MNIST-to-SYND","dataset_url":null,"rows_in_archive":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Butterfly","paper_title":"Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation","paper_url":"/paper/butterfly-robust-one-step-approach-towards","paper_date":"2019-05-19","arxiv_id":"1905.07720","code_links":[{"title":"fengliu90/Butterfly","url":"https://github.com/fengliu90/Butterfly"}],"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-adaptation-on-noisy-synd-to-mnist","slug":"domain-adaptation-on-noisy-synd-to-mnist","dataset":"Noisy-SYND-to-MNIST","dataset_url":null,"rows_in_archive":1,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Butterfly","paper_title":"Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation","paper_url":"/paper/butterfly-robust-one-step-approach-towards","paper_date":"2019-05-19","arxiv_id":"1905.07720","code_links":[{"title":"fengliu90/Butterfly","url":"https://github.com/fengliu90/Butterfly"}],"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-adaptation-on-office-caltech-10","slug":"domain-adaptation-on-office-caltech-10","dataset":"Office-Caltech-10","dataset_url":"/dataset/office-caltech-10","rows_in_archive":1,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"MEDA","paper_title":"Visual Domain Adaptation with Manifold Embedded Distribution Alignment","paper_url":"/paper/visual-domain-adaptation-with-manifold","paper_date":"2018-07-19","arxiv_id":"1807.07258","code_links":[{"title":"jindongwang/transferlearning","url":"https://github.com/jindongwang/transferlearning"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-pacs","slug":"domain-adaptation-on-pacs","dataset":"PACS","dataset_url":"/dataset/pacs","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"SSGEN","paper_title":"Learning to Generalize across Domains on Single Test Samples","paper_url":"/paper/learning-to-generalize-across-domains-on-1","paper_date":"2022-02-16","arxiv_id":"2202.08045","code_links":[{"title":"zzzx1224/singlesamplegeneralization-iclr2022","url":"https://github.com/zzzx1224/singlesamplegeneralization-iclr2022"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-s2rda-49","slug":"domain-adaptation-on-s2rda-49","dataset":"S2RDA-49","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PGA","paper_title":"Enhancing Domain Adaptation through Prompt Gradient Alignment","paper_url":"/paper/enhancing-domain-adaptation-through-prompt","paper_date":"2024-06-13","arxiv_id":"2406.09353","code_links":[{"title":"viethoang1512/pga","url":"https://github.com/viethoang1512/pga"}],"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":12}}},{"leaderboard":"/sota/domain-adaptation-on-s2rda-ms-39","slug":"domain-adaptation-on-s2rda-ms-39","dataset":"S2RDA-MS-39","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PGA","paper_title":"Enhancing Domain Adaptation through Prompt Gradient Alignment","paper_url":"/paper/enhancing-domain-adaptation-through-prompt","paper_date":"2024-06-13","arxiv_id":"2406.09353","code_links":[{"title":"viethoang1512/pga","url":"https://github.com/viethoang1512/pga"}],"syntology":{"n":12,"n_ran":6,"n_unverified":6,"n_pointer_only":12}}},{"leaderboard":"/sota/domain-adaptation-on-sim10k","slug":"domain-adaptation-on-sim10k","dataset":"Sim10k","dataset_url":"/dataset/sim10k","rows_in_archive":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MILA","paper_title":"MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection","paper_url":"/paper/mila-memory-based-instance-level-adaptation-1","paper_date":"2023-11-20","arxiv_id":"2309.01086","code_links":[{"title":"hitachi-rd-cv/MILA","url":"https://github.com/hitachi-rd-cv/MILA"}],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-synth-objects-to-linemod","slug":"domain-adaptation-on-synth-objects-to-linemod","dataset":"Synth Objects-to-LINEMOD","dataset_url":"/dataset/linemod-1","rows_in_archive":1,"metrics":["Classification Accuracy","Mean Angle Error"],"first_row_in_archive_order":{"model":"DSN (DANN)","paper_title":"Domain Separation Networks","paper_url":"/paper/domain-separation-networks","paper_date":"2016-08-22","arxiv_id":"1608.06019","code_links":[{"title":"tensorflow/models","url":"https://github.com/tensorflow/models"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/research/domain_adaptation"},{"title":"fungtion/DSN","url":"https://github.com/fungtion/DSN"},{"title":"AmirHussein96/Simplified-DSN","url":"https://github.com/AmirHussein96/Simplified-DSN"},{"title":"WinChua/CDRTR","url":"https://github.com/WinChua/CDRTR"},{"title":"better-chao/DSN","url":"https://github.com/better-chao/DSN"}],"syntology":{"n":14,"n_ran":5,"n_unverified":9,"n_pointer_only":6}}},{"leaderboard":"/sota/domain-adaptation-on-synthia-to","slug":"domain-adaptation-on-synthia-to","dataset":"SYNTHIA-to-FoggyCityscapes","dataset_url":null,"rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"FogAdapt+","paper_title":"FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images","paper_url":"/paper/leveraging-scale-invariance-and-uncertainity","paper_date":"2022-01-07","arxiv_id":"2201.02588","code_links":[],"syntology":null}},{"leaderboard":"/sota/domain-adaptation-on-synthia-to-cityscapes-1","slug":"domain-adaptation-on-synthia-to-cityscapes-1","dataset":"SYNTHIA-to-Cityscapes Labels","dataset_url":null,"rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"MRNet","paper_title":"Unsupervised Scene Adaptation with Memory Regularization in vivo","paper_url":"/paper/unsupervised-scene-adaptation-with-memory","paper_date":"2019-12-24","arxiv_id":"1912.11164","code_links":[{"title":"layumi/Seg-Uncertainty","url":"https://github.com/layumi/Seg-Uncertainty"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}}},{"leaderboard":"/sota/domain-adaptation-on-viper-to-cityscapes","slug":"domain-adaptation-on-viper-to-cityscapes","dataset":"VIPER-to-Cityscapes","dataset_url":null,"rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"STPL","paper_title":"Spatio-Temporal Pixel-Level Contrastive Learning-based Source-Free Domain Adaptation for Video Semantic Segmentation","paper_url":"/paper/spatio-temporal-pixel-level-contrastive","paper_date":"2023-03-25","arxiv_id":"2303.14361","code_links":[{"title":"shaoyuanlo/stpl","url":"https://github.com/shaoyuanlo/stpl"}],"syntology":null}}],"datasets":[{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/svhn","name":"SVHN","full_name":"Street View House Numbers","num_papers_in_archive":3406},{"url":"/dataset/office-home","name":"Office-Home","full_name":"","num_papers_in_archive":1074},{"url":"/dataset/domainnet","name":"DomainNet","full_name":"DomainNet","num_papers_in_archive":753},{"url":"/dataset/pacs","name":"PACS","full_name":"Photo-Art-Cartoon-Sketch","num_papers_in_archive":668},{"url":"/dataset/office-31","name":"Office-31","full_name":"Office Dataset","num_papers_in_archive":643},{"url":"/dataset/synthia","name":"SYNTHIA","full_name":"SYNTHetic Collection of Imagery and Annotations","num_papers_in_archive":538},{"url":"/dataset/bdd100k","name":"BDD100K","full_name":"","num_papers_in_archive":469},{"url":"/dataset/usps","name":"USPS","full_name":"USPS","num_papers_in_archive":459},{"url":"/dataset/replica","name":"Replica","full_name":"","num_papers_in_archive":414},{"url":"/dataset/gta5","name":"GTA5","full_name":"Grand Theft Auto 5","num_papers_in_archive":412},{"url":"/dataset/gtsrb","name":"GTSRB","full_name":"German Traffic Sign Recognition Benchmark","num_papers_in_archive":374},{"url":"/dataset/imagenet-sketch","name":"ImageNet-Sketch","full_name":"","num_papers_in_archive":268},{"url":"/dataset/foggy-cityscapes","name":"Foggy Cityscapes","full_name":"","num_papers_in_archive":249},{"url":"/dataset/visda-2017","name":"VisDA-2017","full_name":"VisDA-2017","num_papers_in_archive":223},{"url":"/dataset/opensubtitles","name":"OpenSubtitles","full_name":"","num_papers_in_archive":214},{"url":"/dataset/mnist-m","name":"MNIST-M","full_name":"","num_papers_in_archive":193},{"url":"/dataset/fsd50k","name":"FSD50K","full_name":"Freesound Database 50K","num_papers_in_archive":155},{"url":"/dataset/idd","name":"IDD","full_name":"Indian Driving Dataset","num_papers_in_archive":98},{"url":"/dataset/imageclef-da","name":"ImageCLEF-DA","full_name":"ImageCLEF-DA","num_papers_in_archive":96},{"url":"/dataset/vgg-face-1","name":"VGG Face","full_name":"","num_papers_in_archive":94},{"url":"/dataset/sim10k","name":"Sim10k","full_name":"","num_papers_in_archive":92},{"url":"/dataset/aspec","name":"ASPEC","full_name":"Asian Scientific Paper Excerpt Corpus","num_papers_in_archive":87},{"url":"/dataset/loveda","name":"LoveDA","full_name":"Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation","num_papers_in_archive":81},{"url":"/dataset/mtnt","name":"MTNT","full_name":"","num_papers_in_archive":52},{"url":"/dataset/synscapes","name":"Synscapes","full_name":"","num_papers_in_archive":46},{"url":"/dataset/amazon-product-data","name":"Amazon Product Data","full_name":"rithik","num_papers_in_archive":41},{"url":"/dataset/v2v4real","name":"V2V4Real","full_name":"","num_papers_in_archive":35},{"url":"/dataset/linemod-1","name":"LM","full_name":"LINEMOD","num_papers_in_archive":34},{"url":"/dataset/acdc-adverse-conditions-dataset-with","name":"ACDC (Adverse Conditions Dataset with Correspondences)","full_name":"Adverse Conditions Dataset with Correspondences","num_papers_in_archive":31},{"url":"/dataset/avd","name":"AVD","full_name":"Active Vision Dataset","num_papers_in_archive":29},{"url":"/dataset/comic2k","name":"Comic2k","full_name":"","num_papers_in_archive":29},{"url":"/dataset/techqa","name":"TechQA","full_name":"The TechQA Dataset","num_papers_in_archive":24},{"url":"/dataset/kdconv","name":"KdConv","full_name":"Knowledge-driven Conversation","num_papers_in_archive":22},{"url":"/dataset/animal-pose-dataset","name":"Animal-Pose Dataset","full_name":"","num_papers_in_archive":21},{"url":"/dataset/vidit","name":"VIDIT","full_name":"Virtual Image Dataset for Illumination Transfer","num_papers_in_archive":20},{"url":"/dataset/wildplaces","name":"Wild-Places","full_name":"","num_papers_in_archive":18},{"url":"/dataset/jesc","name":"JESC","full_name":"Japanese-English Subtitle Corpus","num_papers_in_archive":17},{"url":"/dataset/vehiclex","name":"VehicleX","full_name":null,"num_papers_in_archive":16},{"url":"/dataset/casia-v2","name":"CASIA V2","full_name":"CASIA V2","num_papers_in_archive":15},{"url":"/dataset/cmu-dog","name":"CMU DoG","full_name":"CMU Document Grounded Conversations Dataset","num_papers_in_archive":15},{"url":"/dataset/crossner","name":"CrossNER","full_name":"","num_papers_in_archive":15},{"url":"/dataset/refuge-challenge","name":"REFUGE Challenge","full_name":"Retinal Fundus Glaucoma Challenge","num_papers_in_archive":14},{"url":"/dataset/multilingual-reuters","name":"Multilingual Reuters","full_name":"Multilingual Reuters Collection","num_papers_in_archive":13},{"url":"/dataset/perspectrum","name":"Perspectrum","full_name":"","num_papers_in_archive":11},{"url":"/dataset/so2sat-lcz42","name":"So2Sat LCZ42","full_name":"","num_papers_in_archive":11},{"url":"/dataset/cropandweed-dataset","name":"CropAndWeed","full_name":"","num_papers_in_archive":10},{"url":"/dataset/office-caltech-10","name":"Office-Caltech-10","full_name":"Office-Caltech-10","num_papers_in_archive":10},{"url":"/dataset/adaptiope","name":"Adaptiope","full_name":"","num_papers_in_archive":9},{"url":"/dataset/mindboggle","name":"Mindboggle","full_name":"","num_papers_in_archive":9},{"url":"/dataset/covidgr","name":"COVIDGR","full_name":null,"num_papers_in_archive":8},{"url":"/dataset/cross-dataset-testbed","name":"Cross-Dataset Testbed","full_name":"Cross-Dataset Testbed","num_papers_in_archive":7},{"url":"/dataset/modern-office-31","name":"Modern Office-31","full_name":"","num_papers_in_archive":6},{"url":"/dataset/ood-cv","name":"OOD-CV","full_name":"Out Of Distribution Generalization in Computer Vision","num_papers_in_archive":6},{"url":"/dataset/plaba","name":"PLABA","full_name":"Plain Language Adaptation of Biomedical Abstracts","num_papers_in_archive":6},{"url":"/dataset/illness-dataset","name":"Illness-dataset","full_name":"Illness multi-domain textual dataset","num_papers_in_archive":5},{"url":"/dataset/libri-adapt","name":"Libri-Adapt","full_name":"","num_papers_in_archive":5},{"url":"/dataset/nlpeer","name":"NLPeer","full_name":"","num_papers_in_archive":5},{"url":"/dataset/pku-reid","name":"PKU-Reid","full_name":null,"num_papers_in_archive":5},{"url":"/dataset/rocog-v2","name":"RoCoG-v2","full_name":"Robot Control Gestures","num_papers_in_archive":5},{"url":"/dataset/sims4action","name":"Sims4Action","full_name":"","num_papers_in_archive":5},{"url":"/dataset/carlane-benchmark","name":"CARLANE Benchmark","full_name":"","num_papers_in_archive":4},{"url":"/dataset/cocodoom","name":"CocoDoom","full_name":"","num_papers_in_archive":4},{"url":"/dataset/flair-french-land-cover-from-aerospace","name":"FLAIR (French Land cover from Aerospace ImageRy)","full_name":"","num_papers_in_archive":4},{"url":"/dataset/human-animal-cartoon","name":"Human-Animal-Cartoon","full_name":"Human-Animal-Cartoon","num_papers_in_archive":4},{"url":"/dataset/nha12d","name":"NHA12D","full_name":"A New Pavement Crack Dataset","num_papers_in_archive":4},{"url":"/dataset/all-day-cityscapes","name":"All-day CityScapes","full_name":"","num_papers_in_archive":3},{"url":"/dataset/five-billion-pixels","name":"Five-Billion-Pixels","full_name":"","num_papers_in_archive":3},{"url":"/dataset/long-term-visual-localization","name":"Long-term visual localization","full_name":"","num_papers_in_archive":3},{"url":"/dataset/stanceosaurus","name":"Stanceosaurus","full_name":"","num_papers_in_archive":3},{"url":"/dataset/thirdtofirst","name":"ThirdToFirst","full_name":"","num_papers_in_archive":3},{"url":"/dataset/youtubean","name":"Youtubean","full_name":null,"num_papers_in_archive":3},{"url":"/dataset/cumulo","name":"Cumulo","full_name":"","num_papers_in_archive":2},{"url":"/dataset/daplankton","name":"DAPlankton","full_name":"","num_papers_in_archive":2},{"url":"/dataset/digital-twin-supported-deep-learning-for","name":"Digital twin-supported deep learning for fault diagnosis","full_name":"","num_papers_in_archive":2},{"url":"/dataset/leukemiaattri","name":"LeukemiaAttri","full_name":"","num_papers_in_archive":2},{"url":"/dataset/mila-simulated-floods","name":"Mila Simulated Floods","full_name":"","num_papers_in_archive":2},{"url":"/dataset/msda","name":"MSDA","full_name":"Multi-source domain adaptation dataset for text recognition","num_papers_in_archive":2},{"url":"/dataset/pano3d","name":"Pano3D","full_name":"","num_papers_in_archive":2},{"url":"/dataset/s2rda","name":"S2RDA","full_name":"","num_papers_in_archive":2},{"url":"/dataset/xl-r2r","name":"XL-R2R","full_name":"Cross-lingual Room-to-Room","num_papers_in_archive":2},{"url":"/dataset/apron-dataset","name":"Apron Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/bladderbatch","name":"bladderbatch","full_name":"bladderbatch","num_papers_in_archive":1},{"url":"/dataset/canon-raw-low-light","name":"Canon RAW Low Light","full_name":"Canon Camera Low Light RAW Image Dataset","num_papers_in_archive":1},{"url":"/dataset/drift","name":"DRIFT","full_name":"Domain-Adaptive Regression for Forest Monitoring","num_papers_in_archive":1},{"url":"/dataset/fgrada","name":"FGraDA","full_name":"Fine-Grained Domain Adaptation Dataset","num_papers_in_archive":1},{"url":"/dataset/infraparis","name":"InfraParis","full_name":"","num_papers_in_archive":1},{"url":"/dataset/lidar-cs","name":"LiDAR-CS","full_name":"","num_papers_in_archive":1},{"url":"/dataset/nikon-camera-low-light-raw-image-dataset","name":"Nikon RAW Low Light","full_name":"Nikon Camera Low Light RAW Image Dataset","num_papers_in_archive":1},{"url":"/dataset/open-mic","name":"Open MIC","full_name":"Open Museum Identification Challenge","num_papers_in_archive":1},{"url":"/dataset/opengda","name":"OpenGDA","full_name":"","num_papers_in_archive":1},{"url":"/dataset/rwanda-built-up-region-segmentation","name":"RWanda Built-up Region Segmentation","full_name":"","num_papers_in_archive":1},{"url":"/dataset/semanticusl","name":"SemanticUSL","full_name":"","num_papers_in_archive":1},{"url":"/dataset/synthetic-keystroke","name":"Synthetic Keystroke","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/wmt-2014-medical","name":"WMT 2014 Medical","full_name":"WMT 2014 Medical Translation Task","num_papers_in_archive":1},{"url":"/dataset/fnirs2mw","name":"fNIRS2MW","full_name":"The Tufts fNIRS to Mental Workload Dataset","num_papers_in_archive":0}],"subtasks":[{"url":"/task/blended-target-domain-adaptation","name":"Blended-target Domain Adaptation"},{"url":"/task/continuously-indexed-domain-adaptation","name":"Continuously Indexed Domain Adaptation"},{"url":"/task/domain-generalization","name":"Domain Generalization"},{"url":"/task/online-domain-adaptation","name":"Online Domain Adaptation"},{"url":"/task/open-set-multi-target-domain-adaptation","name":"Open-Set Multi-Target Domain Adaptation"},{"url":"/task/partial-domain-adaptation","name":"Partial Domain Adaptation"},{"url":"/task/prompt-driven-zero-shot-domain-adaptation","name":"Prompt-driven Zero-shot Domain Adaptation"},{"url":"/task/source-free-domain-adaptation","name":"Source-Free Domain Adaptation"},{"url":"/task/test-time-adaptation","name":"Test-time Adaptation"},{"url":"/task/universal-domain-adaptation","name":"Universal Domain Adaptation"},{"url":"/task/unsupervised-domain-adaptation","name":"Unsupervised Domain Adaptation"},{"url":"/task/video-domain-adapation","name":"Video Domain Adapation"},{"url":"/task/wildly-unsupervised-domain-adaptation","name":"Wildly Unsupervised Domain Adaptation"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":2400,"tagged_in_all":6439,"items":[{"url":"/paper/language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","repositories_listed":67,"syntology":{"n":65,"n_ran":15,"n_unverified":50,"n_pointer_only":4}},{"url":"/paper/domain-adversarial-training-of-neural","title":"Domain-Adversarial Training of Neural Networks","date":"2015-05-28","arxiv_id":"1505.07818","repositories_listed":37,"syntology":{"n":52,"n_ran":33,"n_unverified":19,"n_pointer_only":22}},{"url":"/paper/superpoint-self-supervised-interest-point","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","date":"2017-12-20","arxiv_id":"1712.07629","repositories_listed":36,"syntology":{"n":11,"n_ran":11,"n_unverified":0,"n_pointer_only":6}},{"url":"/paper/generalized-end-to-end-loss-for-speaker","title":"Generalized End-to-End Loss for Speaker Verification","date":"2017-10-28","arxiv_id":"1710.10467","repositories_listed":30,"syntology":{"n":27,"n_ran":4,"n_unverified":23,"n_pointer_only":1}},{"url":"/paper/two-at-once-enhancing-learning-and","title":"Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net","date":"2018-07-25","arxiv_id":"1807.09441","repositories_listed":25,"syntology":{"n":16,"n_ran":4,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/unsupervised-domain-adaptation-by","title":"Unsupervised Domain Adaptation by Backpropagation","date":"2014-09-26","arxiv_id":"1409.7495","repositories_listed":22,"syntology":{"n":41,"n_ran":34,"n_unverified":7,"n_pointer_only":14}},{"url":"/paper/adversarial-discriminative-domain-adaptation","title":"Adversarial Discriminative Domain Adaptation","date":"2017-02-17","arxiv_id":"1702.05464","repositories_listed":20,"syntology":{"n":48,"n_ran":14,"n_unverified":34,"n_pointer_only":12}},{"url":"/paper/learning-to-adapt-structured-output-space-for","title":"Learning to Adapt Structured Output Space for Semantic Segmentation","date":"2018-02-28","arxiv_id":"1802.10349","repositories_listed":12,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/learning-generalisable-omni-scale","title":"Learning Generalisable Omni-Scale Representations for Person Re-Identification","date":"2019-10-15","arxiv_id":"1910.06827","repositories_listed":9,"syntology":{"n":9,"n_ran":6,"n_unverified":3,"n_pointer_only":6}},{"url":"/paper/maximum-classifier-discrepancy-for","title":"Maximum Classifier Discrepancy for Unsupervised Domain Adaptation","date":"2017-12-07","arxiv_id":"1712.02560","repositories_listed":9,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/learning-from-simulated-and-unsupervised","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","date":"2016-12-22","arxiv_id":"1612.07828","repositories_listed":9,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/deep-coral-correlation-alignment-for-deep","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","date":"2016-07-06","arxiv_id":"1607.01719","repositories_listed":9,"syntology":{"n":16,"n_ran":10,"n_unverified":6,"n_pointer_only":10}},{"url":"/paper/domain-adaptation-for-structured-output-via","title":"Domain Adaptation for Structured Output via Discriminative Patch Representations","date":"2019-01-16","arxiv_id":"1901.05427","repositories_listed":8,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/domain-adaptive-faster-r-cnn-for-object","title":"Domain Adaptive Faster R-CNN for Object Detection in the Wild","date":"2018-03-08","arxiv_id":"1803.03243","repositories_listed":8,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":4}},{"url":"/paper/wasserstein-distance-guided-representation","title":"Wasserstein Distance Guided Representation Learning for Domain Adaptation","date":"2017-07-05","arxiv_id":"1707.01217","repositories_listed":8,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/unsupervised-image-to-image-translation","title":"Unsupervised Image-to-Image Translation Networks","date":"2017-03-02","arxiv_id":"1703.00848","repositories_listed":8,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":1}},{"url":"/paper/decaf-a-deep-convolutional-activation-feature","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","date":"2013-10-06","arxiv_id":"1310.1531","repositories_listed":8,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/fine-tuning-large-language-models-for-domain-1","title":"Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities","date":"2024-09-05","arxiv_id":"2409.03444","repositories_listed":7,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/rescaling-egocentric-vision","title":"Rescaling Egocentric Vision","date":"2020-06-23","arxiv_id":"2006.13256","repositories_listed":7,"syntology":{"n":18,"n_ran":3,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/agnostic-federated-learning","title":"Agnostic Federated Learning","date":"2019-02-01","arxiv_id":"1902.00146","repositories_listed":7,"syntology":{"n":10,"n_ran":3,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/multi-task-deep-neural-networks-for-natural","title":"Multi-Task Deep Neural Networks for Natural Language Understanding","date":"2019-01-31","arxiv_id":"1901.11504","repositories_listed":7,"syntology":{"n":13,"n_ran":5,"n_unverified":8,"n_pointer_only":2}},{"url":"/paper/diverse-image-to-image-translation-via","title":"Diverse Image-to-Image Translation via Disentangled Representations","date":"2018-08-02","arxiv_id":"1808.00948","repositories_listed":7,"syntology":null},{"url":"/paper/deep-hashing-network-for-unsupervised-domain","title":"Deep Hashing Network for Unsupervised Domain Adaptation","date":"2017-06-22","arxiv_id":"1706.07522","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/deep-domain-confusion-maximizing-for-domain","title":"Deep Domain Confusion: Maximizing for Domain Invariance","date":"2014-12-10","arxiv_id":"1412.3474","repositories_listed":7,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/flow-straight-and-fast-learning-to-generate","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","date":"2022-09-07","arxiv_id":"2209.03003","repositories_listed":6,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":6}},{"url":"/paper/adamatch-a-unified-approach-to-semi","title":"AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation","date":"2021-06-08","arxiv_id":"2106.04732","repositories_listed":6,"syntology":{"n":20,"n_ran":8,"n_unverified":12,"n_pointer_only":9}},{"url":"/paper/tsdae-using-transformer-based-sequential","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","date":"2021-04-14","arxiv_id":"2104.06979","repositories_listed":6,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/pseudolikelihood-reranking-with-masked","title":"Masked Language Model Scoring","date":"2019-10-31","arxiv_id":"1910.14659","repositories_listed":6,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":3}},{"url":"/paper/bridging-theory-and-algorithm-for-domain","title":"Bridging Theory and Algorithm for Domain Adaptation","date":"2019-04-11","arxiv_id":"1904.05801","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/multi-adversarial-domain-adaptation","title":"Multi-Adversarial Domain Adaptation","date":"2018-09-04","arxiv_id":"1809.02176","repositories_listed":6,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}],"syntology_records":29,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}