{"url":"/task/domain-generalization","name":"Domain Generalization","slug":"domain-generalization","description_markdown":"The idea of **Domain Generalization** is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain\n\n\n<span class=\"description-source\">Source: [Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning ](https://arxiv.org/abs/2004.10780)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1751,"papers_with_code":859,"benchmarks":21,"benchmark_tables_in_archive":21,"benchmark_tables_shown":21,"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":31,"subtasks":3,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/domain-generalization-on-pacs-2","slug":"domain-generalization-on-pacs-2","dataset":"PACS","dataset_url":"/dataset/pacs","rows_in_archive":133,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"SIMPLE+","paper_title":"SIMPLE: Specialized Model-Sample Matching for Domain Generalization","paper_url":"/paper/simple-specialized-model-sample-matching-for","paper_date":"2023-05-01","arxiv_id":null,"code_links":[{"title":"microsoft/SeqML","url":"https://github.com/microsoft/SeqML/tree/main/SIMPLE"}],"syntology":null}},{"leaderboard":"/sota/domain-generalization-on-vizwiz","slug":"domain-generalization-on-vizwiz","dataset":"VizWiz-Classification","dataset_url":"/dataset/vizwiz-classification","rows_in_archive":90,"metrics":["Accuracy - All Images","Accuracy - Corrupted Images","Accuracy - Clean Images"],"first_row_in_archive_order":{"model":"VOLO-D5","paper_title":"VOLO: Vision Outlooker for Visual Recognition","paper_url":"/paper/volo-vision-outlooker-for-visual-recognition","paper_date":"2021-06-24","arxiv_id":"2106.13112","code_links":[{"title":"rwightman/pytorch-image-models","url":"https://github.com/rwightman/pytorch-image-models"},{"title":"xmu-xiaoma666/External-Attention-pytorch","url":"https://github.com/xmu-xiaoma666/External-Attention-pytorch/blob/master/attention/OutlookAttention.py"},{"title":"BR-IDL/PaddleViT","url":"https://github.com/BR-IDL/PaddleViT/blob/main/image_classification/VOLO"},{"title":"sail-sg/volo","url":"https://github.com/sail-sg/volo"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/volo"},{"title":"mindspore-courses/External-Attention-MindSpore","url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/attention/OutlookAttention.py"},{"title":"mindspore-courses/External-Attention-MindSpore","url":"https://github.com/mindspore-courses/External-Attention-MindSpore/blob/main/model/backbone/VOLO.py"}],"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-generalization-on-imagenet-c","slug":"domain-generalization-on-imagenet-c","dataset":"ImageNet-C","dataset_url":"/dataset/imagenet-c","rows_in_archive":47,"metrics":["mean Corruption Error (mCE)","Top 1 Accuracy","Number of params"],"first_row_in_archive_order":{"model":"DINOv2 (ViT-g/14, frozen model, linear eval)","paper_title":"DINOv2: Learning Robust Visual Features without Supervision","paper_url":"/paper/dinov2-learning-robust-visual-features","paper_date":"2023-04-14","arxiv_id":"2304.07193","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"facebookresearch/dinov2","url":"https://github.com/facebookresearch/dinov2"},{"title":"roboflow/rf-detr","url":"https://github.com/roboflow/rf-detr"},{"title":"open-edge-platform/training_extensions","url":"https://github.com/open-edge-platform/training_extensions"},{"title":"OML-Team/open-metric-learning","url":"https://github.com/OML-Team/open-metric-learning"},{"title":"leondgarse/keras_cv_attention_models","url":"https://github.com/leondgarse/keras_cv_attention_models/tree/main/keras_cv_attention_models/beit"},{"title":"fabio-sim/Depth-Anything-ONNX","url":"https://github.com/fabio-sim/Depth-Anything-ONNX"},{"title":"open-edge-platform/geti","url":"https://github.com/open-edge-platform/geti"},{"title":"facebookresearch/highrescanopyheight","url":"https://github.com/facebookresearch/highrescanopyheight"},{"title":"PaddlePaddle/PASSL","url":"https://github.com/PaddlePaddle/PASSL"},{"title":"beneroth13/dinov2","url":"https://github.com/beneroth13/dinov2"},{"title":"mohammedsb/dinov2formedical","url":"https://github.com/mohammedsb/dinov2formedical"},{"title":"marrlab/dinobloom","url":"https://github.com/marrlab/dinobloom"},{"title":"bespontaneous/proteus-pytorch","url":"https://github.com/bespontaneous/proteus-pytorch"},{"title":"ByungKwanLee/Causal-Unsupervised-Segmentation","url":"https://github.com/ByungKwanLee/Causal-Unsupervised-Segmentation"},{"title":"zhu-xlab/softcon","url":"https://github.com/zhu-xlab/softcon"},{"title":"birder/birder","url":"https://gitlab.com/birder/birder"},{"title":"gorkaydemir/DINOSAUR","url":"https://github.com/gorkaydemir/DINOSAUR"},{"title":"seatizendoi/dinovdeau","url":"https://github.com/seatizendoi/dinovdeau"},{"title":"BurguerJohn/global_perceptual_similarity_loss","url":"https://github.com/BurguerJohn/global_perceptual_similarity_loss"},{"title":"buyeah1109/KEN","url":"https://github.com/buyeah1109/KEN"},{"title":"JHKim-snu/PGA","url":"https://github.com/JHKim-snu/PGA"},{"title":"BurguerJohn/torch-felix","url":"https://github.com/BurguerJohn/torch-felix"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/dinov2"},{"title":"buyeah1109/finc","url":"https://github.com/buyeah1109/finc"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/dinov2"}],"syntology":{"n":46,"n_ran":21,"n_unverified":25,"n_pointer_only":12}}},{"leaderboard":"/sota/domain-generalization-on-office-home","slug":"domain-generalization-on-office-home","dataset":"Office-Home","dataset_url":"/dataset/office-home","rows_in_archive":45,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"MoA (OpenCLIP, ViT-B/16)","paper_title":"Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters","paper_url":"/paper/domain-generalization-using-large-pretrained","paper_date":"2023-10-17","arxiv_id":"2310.11031","code_links":[{"title":"KU-CVLAB/MoA","url":"https://github.com/KU-CVLAB/MoA"}],"syntology":null}},{"leaderboard":"/sota/domain-generalization-on-imagenet-a","slug":"domain-generalization-on-imagenet-a","dataset":"ImageNet-A","dataset_url":"/dataset/imagenet-a","rows_in_archive":39,"metrics":["Top-1 accuracy %","Number of params"],"first_row_in_archive_order":{"model":"Model soups (BASIC-L)","paper_title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","paper_url":"/paper/model-soups-averaging-weights-of-multiple","paper_date":"2022-03-10","arxiv_id":"2203.05482","code_links":[{"title":"mlfoundations/model-soups","url":"https://github.com/mlfoundations/model-soups"},{"title":"Burf/ModelSoups","url":"https://github.com/Burf/ModelSoups"},{"title":"facebookresearch/ModelRatatouille","url":"https://github.com/facebookresearch/ModelRatatouille"},{"title":"hwk0702/keras2torch","url":"https://github.com/hwk0702/keras2torch/tree/main/Computer_Vision/Model_Soup"},{"title":"flowritecom/flow-merge","url":"https://github.com/flowritecom/flow-merge"},{"title":"shallowlearn/sportsreid","url":"https://github.com/shallowlearn/sportsreid"}],"syntology":{"n":17,"n_ran":5,"n_unverified":12,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-generalization-on-imagenet-r","slug":"domain-generalization-on-imagenet-r","dataset":"ImageNet-R","dataset_url":"/dataset/imagenet-r","rows_in_archive":39,"metrics":["Top-1 Error Rate"],"first_row_in_archive_order":{"model":"Model soups (BASIC-L)","paper_title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","paper_url":"/paper/model-soups-averaging-weights-of-multiple","paper_date":"2022-03-10","arxiv_id":"2203.05482","code_links":[{"title":"mlfoundations/model-soups","url":"https://github.com/mlfoundations/model-soups"},{"title":"Burf/ModelSoups","url":"https://github.com/Burf/ModelSoups"},{"title":"facebookresearch/ModelRatatouille","url":"https://github.com/facebookresearch/ModelRatatouille"},{"title":"hwk0702/keras2torch","url":"https://github.com/hwk0702/keras2torch/tree/main/Computer_Vision/Model_Soup"},{"title":"flowritecom/flow-merge","url":"https://github.com/flowritecom/flow-merge"},{"title":"shallowlearn/sportsreid","url":"https://github.com/shallowlearn/sportsreid"}],"syntology":{"n":17,"n_ran":5,"n_unverified":12,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-generalization-on-domainnet","slug":"domain-generalization-on-domainnet","dataset":"DomainNet","dataset_url":"/dataset/domainnet","rows_in_archive":38,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"L2C (CLIP, ViT-L/14)","paper_title":"Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation","paper_url":"/paper/learning-to-adapt-frozen-clip-for-few-shot","paper_date":"2025-01-15","arxiv_id":null,"code_links":[{"title":"chi-chi-zx/L2C","url":"https://github.com/chi-chi-zx/L2C"}],"syntology":null}},{"leaderboard":"/sota/domain-generalization-on-vlcs","slug":"domain-generalization-on-vlcs","dataset":"VLCS","dataset_url":"/dataset/vlcs","rows_in_archive":37,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"CAR-FT (CLIP, ViT-B/16)","paper_title":"Context-Aware Robust Fine-Tuning","paper_url":"/paper/context-aware-robust-fine-tuning","paper_date":"2022-11-29","arxiv_id":"2211.16175","code_links":[],"syntology":null}},{"leaderboard":"/sota/domain-generalization-on-terraincognita","slug":"domain-generalization-on-terraincognita","dataset":"TerraIncognita","dataset_url":null,"rows_in_archive":30,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"UniDG + CORAL + ConvNeXt-B","paper_title":"Towards Unified and Effective Domain Generalization","paper_url":"/paper/towards-unified-and-effective-domain","paper_date":"2023-10-16","arxiv_id":"2310.10008","code_links":[{"title":"invictus717/UniDG","url":"https://github.com/invictus717/UniDG"}],"syntology":null}},{"leaderboard":"/sota/domain-generalization-on-gta-to-avg","slug":"domain-generalization-on-gta-to-avg","dataset":"GTA-to-Avg(Cityscapes,BDD,Mapillary)","dataset_url":null,"rows_in_archive":24,"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-generalization-on-imagenet-sketch","slug":"domain-generalization-on-imagenet-sketch","dataset":"ImageNet-Sketch","dataset_url":"/dataset/imagenet-sketch","rows_in_archive":20,"metrics":["Top-1 accuracy"],"first_row_in_archive_order":{"model":"Model soups (BASIC-L)","paper_title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","paper_url":"/paper/model-soups-averaging-weights-of-multiple","paper_date":"2022-03-10","arxiv_id":"2203.05482","code_links":[{"title":"mlfoundations/model-soups","url":"https://github.com/mlfoundations/model-soups"},{"title":"Burf/ModelSoups","url":"https://github.com/Burf/ModelSoups"},{"title":"facebookresearch/ModelRatatouille","url":"https://github.com/facebookresearch/ModelRatatouille"},{"title":"hwk0702/keras2torch","url":"https://github.com/hwk0702/keras2torch/tree/main/Computer_Vision/Model_Soup"},{"title":"flowritecom/flow-merge","url":"https://github.com/flowritecom/flow-merge"},{"title":"shallowlearn/sportsreid","url":"https://github.com/shallowlearn/sportsreid"}],"syntology":{"n":17,"n_ran":5,"n_unverified":12,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-generalization-on-gta5-to-cityscapes","slug":"domain-generalization-on-gta5-to-cityscapes","dataset":"GTA5-to-Cityscapes","dataset_url":null,"rows_in_archive":8,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"tqdm (EVA02-CLIP-L)","paper_title":"Textual Query-Driven Mask Transformer for Domain Generalized Segmentation","paper_url":"/paper/textual-query-driven-mask-transformer-for","paper_date":"2024-07-12","arxiv_id":"2407.09033","code_links":[{"title":"ByeongHyunPak/tqdm","url":"https://github.com/ByeongHyunPak/tqdm"}],"syntology":null}},{"leaderboard":"/sota/domain-generalization-on-nico-animal","slug":"domain-generalization-on-nico-animal","dataset":"NICO Animal","dataset_url":"/dataset/nico","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"NAS-OoD","paper_title":"NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization","paper_url":"/paper/nas-ood-neural-architecture-search-for-out-of","paper_date":"2021-09-05","arxiv_id":"2109.02038","code_links":[{"title":"HaoyueBaiZJU/NAS-OoD","url":"https://github.com/HaoyueBaiZJU/NAS-OoD"}],"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":6}}},{"leaderboard":"/sota/domain-generalization-on-nico-vehicle","slug":"domain-generalization-on-nico-vehicle","dataset":"NICO Vehicle","dataset_url":"/dataset/nico","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"NAS-OoD","paper_title":"NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization","paper_url":"/paper/nas-ood-neural-architecture-search-for-out-of","paper_date":"2021-09-05","arxiv_id":"2109.02038","code_links":[{"title":"HaoyueBaiZJU/NAS-OoD","url":"https://github.com/HaoyueBaiZJU/NAS-OoD"}],"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":6}}},{"leaderboard":"/sota/domain-generalization-on-stylized-imagenet","slug":"domain-generalization-on-stylized-imagenet","dataset":"Stylized-ImageNet","dataset_url":null,"rows_in_archive":3,"metrics":["Top 1 Accuracy"],"first_row_in_archive_order":{"model":"MAE+DAT (ViT-H)","paper_title":"Enhance the Visual Representation via Discrete Adversarial Training","paper_url":"/paper/enhance-the-visual-representation-via","paper_date":"2022-09-16","arxiv_id":"2209.07735","code_links":[{"title":"alibaba/easyrobust","url":"https://github.com/alibaba/easyrobust/tree/main/examples/imageclassification/imagenet/dat"}],"syntology":{"n":11,"n_ran":10,"n_unverified":1,"n_pointer_only":1}}},{"leaderboard":"/sota/domain-generalization-on-rotated-fashion","slug":"domain-generalization-on-rotated-fashion","dataset":"Rotated Fashion-MNIST","dataset_url":"/dataset/fashion-mnist","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MatchDG","paper_title":"Domain Generalization using Causal Matching","paper_url":"/paper/domain-generalization-using-causal-matching-1","paper_date":"2020-06-12","arxiv_id":"2006.07500","code_links":[{"title":"microsoft/robustdg","url":"https://github.com/microsoft/robustdg"}],"syntology":{"n":9,"n_ran":4,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-generalization-on-cifar-100c","slug":"domain-generalization-on-cifar-100c","dataset":"CIFAR-100C","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GLOT-DR","paper_title":"Global-Local Regularization Via Distributional Robustness","paper_url":"/paper/global-local-regularization-via","paper_date":"2022-03-01","arxiv_id":"2203.00553","code_links":[{"title":"viethoang1512/glot","url":"https://github.com/viethoang1512/glot"}],"syntology":null}},{"leaderboard":"/sota/domain-generalization-on-cifar-10c","slug":"domain-generalization-on-cifar-10c","dataset":"CIFAR-10C","dataset_url":"/dataset/cifar-10c","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GLOT-DR","paper_title":"Global-Local Regularization Via Distributional Robustness","paper_url":"/paper/global-local-regularization-via","paper_date":"2022-03-01","arxiv_id":"2203.00553","code_links":[{"title":"viethoang1512/glot","url":"https://github.com/viethoang1512/glot"}],"syntology":null}},{"leaderboard":"/sota/domain-generalization-on-cityscapes-to-acdc","slug":"domain-generalization-on-cityscapes-to-acdc","dataset":"Cityscapes to ACDC","dataset_url":"/dataset/acdc-adverse-conditions-dataset-with","rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"ADSI","paper_title":"Domain Generalization through Attenuation of Domain-Specific Information","paper_url":"/paper/domain-generalization-through-attenuation-of","paper_date":"2025-04-09","arxiv_id":"2504.06781","code_links":[{"title":"ReijiSoftmaxSaito/ADSI","url":"https://github.com/ReijiSoftmaxSaito/ADSI"}],"syntology":null}},{"leaderboard":"/sota/domain-generalization-on-lipitk","slug":"domain-generalization-on-lipitk","dataset":"LipitK","dataset_url":null,"rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"CSD (Ours)","paper_title":"Efficient Domain Generalization via Common-Specific Low-Rank Decomposition","paper_url":"/paper/efficient-domain-generalization-via-common","paper_date":"2020-03-28","arxiv_id":"2003.12815","code_links":[{"title":"vihari/csd","url":"https://github.com/vihari/csd"},{"title":"MindSpore-paper-code-3/code8","url":"https://github.com/MindSpore-paper-code-3/code8/tree/main/csd"}],"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}}},{"leaderboard":"/sota/domain-generalization-on-wilddash","slug":"domain-generalization-on-wilddash","dataset":"WildDash","dataset_url":"/dataset/wilddash","rows_in_archive":1,"metrics":["Mean IoU"],"first_row_in_archive_order":{"model":"ITEN","paper_title":"Exploiting Image Translations via Ensemble Self-Supervised Learning for Unsupervised Domain Adaptation","paper_url":"/paper/exploiting-image-translations-via-ensemble","paper_date":"2021-07-13","arxiv_id":"2107.06235","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/cityscapes","name":"Cityscapes","full_name":"","num_papers_in_archive":3702},{"url":"/dataset/fashion-mnist","name":"Fashion-MNIST","full_name":"","num_papers_in_archive":3202},{"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/imagenet-c","name":"ImageNet-C","full_name":"ImageNet-C","num_papers_in_archive":602},{"url":"/dataset/cifar-10c","name":"CIFAR-10C","full_name":"","num_papers_in_archive":494},{"url":"/dataset/imagenet-r","name":"ImageNet-R","full_name":"ImageNet-Rendition","num_papers_in_archive":481},{"url":"/dataset/imagenet-a","name":"ImageNet-A","full_name":"","num_papers_in_archive":431},{"url":"/dataset/imagenet-sketch","name":"ImageNet-Sketch","full_name":"","num_papers_in_archive":268},{"url":"/dataset/shape-bias","name":"shape bias","full_name":"","num_papers_in_archive":120},{"url":"/dataset/stylized-imagenet","name":"Stylized ImageNet","full_name":"Stylized ImageNet","num_papers_in_archive":106},{"url":"/dataset/wilddash","name":"WildDash","full_name":"","num_papers_in_archive":47},{"url":"/dataset/vlcs","name":"VLCS","full_name":"","num_papers_in_archive":33},{"url":"/dataset/imagenet-p","name":"ImageNet-P","full_name":"","num_papers_in_archive":32},{"url":"/dataset/nico-1","name":"NICO++","full_name":"","num_papers_in_archive":32},{"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/vizwiz-classification","name":"VizWiz-Classification","full_name":"","num_papers_in_archive":22},{"url":"/dataset/msk","name":"MSK","full_name":"MSK","num_papers_in_archive":15},{"url":"/dataset/super-clevr","name":"Super-CLEVR","full_name":"","num_papers_in_archive":13},{"url":"/dataset/nico","name":"NICO","full_name":"Non-I.I.D. Image dataset with Contexts","num_papers_in_archive":9},{"url":"/dataset/wild-time","name":"Wild-Time","full_name":"","num_papers_in_archive":6},{"url":"/dataset/sims4action","name":"Sims4Action","full_name":"","num_papers_in_archive":5},{"url":"/dataset/bioscan-5m","name":"BIOSCAN-5M","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/all-day-cityscapes","name":"All-day CityScapes","full_name":"","num_papers_in_archive":3},{"url":"/dataset/cfc","name":"CFC","full_name":"Caltech Fish Counting Dataset","num_papers_in_archive":3},{"url":"/dataset/prostate-mri-segmentation-dataset","name":"Prostate MRI Segmentation Dataset","full_name":null,"num_papers_in_archive":3},{"url":"/dataset/whyshift","name":"WHYSHIFT","full_name":"","num_papers_in_archive":3},{"url":"/dataset/domain-independent-anomalies-datasets","name":"Domain-independent anomalies datasets","full_name":"Domain-independent anomalies datasets (adaptions of the MVTec Anomaly Detection dataset)","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/evolving-domain-generalization","name":"Evolving Domain Generalization"},{"url":"/task/single-source-domain-generalization","name":"Single-Source Domain Generalization"},{"url":"/task/source-free-domain-generalization","name":"Source-free Domain Generalization"}],"parent_tasks":[{"url":"/task/domain-adaptation","name":"Domain Adaptation"}],"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":859,"tagged_in_all":1751,"items":[{"url":"/paper/deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","arxiv_id":"1512.03385","repositories_listed":484,"syntology":{"n":377,"n_ran":230,"n_unverified":147,"n_pointer_only":187}},{"url":"/paper/very-deep-convolutional-networks-for-large","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","date":"2014-09-04","arxiv_id":"1409.1556","repositories_listed":305,"syntology":{"n":122,"n_ran":12,"n_unverified":110,"n_pointer_only":4}},{"url":"/paper/efficientnet-rethinking-model-scaling-for","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","date":"2019-05-28","arxiv_id":"1905.11946","repositories_listed":144,"syntology":{"n":302,"n_ran":171,"n_unverified":131,"n_pointer_only":112}},{"url":"/paper/mixup-beyond-empirical-risk-minimization","title":"mixup: Beyond Empirical Risk Minimization","date":"2017-10-25","arxiv_id":"1710.09412","repositories_listed":71,"syntology":{"n":47,"n_ran":30,"n_unverified":17,"n_pointer_only":15}},{"url":"/paper/aggregated-residual-transformations-for-deep","title":"Aggregated Residual Transformations for Deep Neural Networks","date":"2016-11-16","arxiv_id":"1611.05431","repositories_listed":61,"syntology":{"n":80,"n_ran":34,"n_unverified":46,"n_pointer_only":13}},{"url":"/paper/masked-autoencoders-are-scalable-vision","title":"Masked Autoencoders Are Scalable Vision Learners","date":"2021-11-11","arxiv_id":"2111.06377","repositories_listed":58,"syntology":{"n":137,"n_ran":71,"n_unverified":66,"n_pointer_only":73}},{"url":"/paper/a-convnet-for-the-2020s","title":"A ConvNet for the 2020s","date":"2022-01-10","arxiv_id":"2201.03545","repositories_listed":54,"syntology":{"n":80,"n_ran":54,"n_unverified":26,"n_pointer_only":11}},{"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/autoaugment-learning-augmentation-policies","title":"AutoAugment: Learning Augmentation Policies from Data","date":"2018-05-24","arxiv_id":"1805.09501","repositories_listed":33,"syntology":{"n":43,"n_ran":6,"n_unverified":37,"n_pointer_only":2}},{"url":"/paper/cutmix-regularization-strategy-to-train","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","date":"2019-05-13","arxiv_id":"1905.04899","repositories_listed":30,"syntology":{"n":24,"n_ran":17,"n_unverified":7,"n_pointer_only":5}},{"url":"/paper/bag-of-tricks-for-image-classification-with","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","date":"2018-12-04","arxiv_id":"1812.01187","repositories_listed":28,"syntology":{"n":15,"n_ran":4,"n_unverified":11,"n_pointer_only":5}},{"url":"/paper/improved-regularization-of-convolutional","title":"Improved Regularization of Convolutional Neural Networks with Cutout","date":"2017-08-15","arxiv_id":"1708.04552","repositories_listed":28,"syntology":{"n":24,"n_ran":21,"n_unverified":3,"n_pointer_only":5}},{"url":"/paper/dinov2-learning-robust-visual-features","title":"DINOv2: Learning Robust Visual Features without Supervision","date":"2023-04-14","arxiv_id":"2304.07193","repositories_listed":26,"syntology":{"n":46,"n_ran":21,"n_unverified":25,"n_pointer_only":12}},{"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/randaugment-practical-data-augmentation-with","title":"RandAugment: Practical automated data augmentation with a reduced search space","date":"2019-09-30","arxiv_id":"1909.13719","repositories_listed":19,"syntology":{"n":65,"n_ran":58,"n_unverified":7,"n_pointer_only":17}},{"url":"/paper/learning-to-prompt-for-vision-language-models","title":"Learning to Prompt for Vision-Language Models","date":"2021-09-02","arxiv_id":"2109.01134","repositories_listed":18,"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/invariant-risk-minimization","title":"Invariant Risk Minimization","date":"2019-07-05","arxiv_id":"1907.02893","repositories_listed":18,"syntology":{"n":30,"n_ran":18,"n_unverified":12,"n_pointer_only":10}},{"url":"/paper/augmix-a-simple-data-processing-method-to","title":"AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty","date":"2019-12-05","arxiv_id":"1912.02781","repositories_listed":15,"syntology":{"n":51,"n_ran":43,"n_unverified":8,"n_pointer_only":25}},{"url":"/paper/resnet-strikes-back-an-improved-training","title":"ResNet strikes back: An improved training procedure in timm","date":"2021-10-01","arxiv_id":"2110.00476","repositories_listed":14,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/benchmarking-neural-network-robustness-to-2","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","date":"2019-03-28","arxiv_id":"1903.12261","repositories_listed":14,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/a-closer-look-at-few-shot-classification-1","title":"A Closer Look at Few-shot Classification","date":"2019-04-08","arxiv_id":"1904.04232","repositories_listed":13,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/conditional-prompt-learning-for-vision","title":"Conditional Prompt Learning for Vision-Language Models","date":"2022-03-10","arxiv_id":"2203.05557","repositories_listed":12,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/in-search-of-lost-domain-generalization","title":"In Search of Lost Domain Generalization","date":"2020-07-02","arxiv_id":"2007.01434","repositories_listed":12,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/on-the-limits-of-cross-domain-generalization","title":"On the limits of cross-domain generalization in automated X-ray prediction","date":"2020-02-06","arxiv_id":"2002.02497","repositories_listed":9,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"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/metaformer-baselines-for-vision","title":"MetaFormer Baselines for Vision","date":"2022-10-24","arxiv_id":"2210.13452","repositories_listed":8,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/self-challenging-improves-cross-domain","title":"Self-Challenging Improves Cross-Domain Generalization","date":"2020-07-05","arxiv_id":"2007.02454","repositories_listed":8,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/distributionally-robust-neural-networks-for","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","date":"2019-11-20","arxiv_id":"1911.08731","repositories_listed":8,"syntology":{"n":10,"n_ran":9,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/volo-vision-outlooker-for-visual-recognition","title":"VOLO: Vision Outlooker for Visual Recognition","date":"2021-06-24","arxiv_id":"2106.13112","repositories_listed":7,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/190411486","title":"Making Convolutional Networks Shift-Invariant Again","date":"2019-04-25","arxiv_id":"1904.11486","repositories_listed":7,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":3}}],"syntology_records":30,"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"}}