{"url":"/task/synthetic-to-real-translation","name":"Synthetic-to-Real Translation","slug":"synthetic-to-real-translation","description_markdown":"Synthetic-to-real translation is the task of domain adaptation from synthetic (or virtual) data to real data.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [CYCADA](https://arxiv.org/pdf/1711.03213v3.pdf) )</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":68,"papers_with_code":58,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/synthetic-to-real-translation-on-gtav-to","slug":"synthetic-to-real-translation-on-gtav-to","dataset":"GTAV-to-Cityscapes Labels","dataset_url":"/dataset/gta5","rows_in_archive":73,"metrics":["mIoU","Per-pixel Accuracy","fwIOU"],"first_row_in_archive_order":{"model":"DCF","paper_title":"Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation","paper_url":"/paper/transferring-to-real-world-layouts-a-depth","paper_date":"2023-11-21","arxiv_id":"2311.12682","code_links":[{"title":"chen742/PiPa","url":"https://github.com/chen742/PiPa"},{"title":"chen742/DCF","url":"https://github.com/chen742/DCF"}],"syntology":null}},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-1","slug":"synthetic-to-real-translation-on-synthia-to-1","dataset":"SYNTHIA-to-Cityscapes","dataset_url":"/dataset/synthia","rows_in_archive":38,"metrics":["MIoU (16 classes)","MIoU (13 classes)"],"first_row_in_archive_order":{"model":"DCF","paper_title":"Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation","paper_url":"/paper/transferring-to-real-world-layouts-a-depth","paper_date":"2023-11-21","arxiv_id":"2311.12682","code_links":[{"title":"chen742/PiPa","url":"https://github.com/chen742/PiPa"},{"title":"chen742/DCF","url":"https://github.com/chen742/DCF"}],"syntology":null}},{"leaderboard":"/sota/synthetic-to-real-translation-on-syn2real-c","slug":"synthetic-to-real-translation-on-syn2real-c","dataset":"Syn2Real-C","dataset_url":"/dataset/syn2real","rows_in_archive":6,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"DADA","paper_title":"Discriminative Adversarial Domain Adaptation","paper_url":"/paper/discriminative-adversarial-domain-adaptation","paper_date":"2019-11-27","arxiv_id":"1911.12036","code_links":[{"title":"huitangtang/DADA-AAAI2020","url":"https://github.com/huitangtang/DADA-AAAI2020"},{"title":"monkey0head/Domain_Adaptation_thesis","url":"https://github.com/monkey0head/Domain_Adaptation_thesis"}],"syntology":null}},{"leaderboard":"/sota/synthetic-to-real-translation-on-synthia-to-2","slug":"synthetic-to-real-translation-on-synthia-to-2","dataset":"SYNTHIA-to-Cityscapes Labels","dataset_url":null,"rows_in_archive":2,"metrics":["mIOU"],"first_row_in_archive_order":{"model":"ELDA","paper_title":"ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA","paper_url":"/paper/elda-using-edges-to-have-an-edge-on-semantic","paper_date":"2022-11-16","arxiv_id":"2211.08888","code_links":[{"title":"TingHLiao/ELDA","url":"https://github.com/TingHLiao/ELDA"}],"syntology":null}}],"datasets":[{"url":"/dataset/synthia","name":"SYNTHIA","full_name":"SYNTHetic Collection of Imagery and Annotations","num_papers_in_archive":538},{"url":"/dataset/gta5","name":"GTA5","full_name":"Grand Theft Auto 5","num_papers_in_archive":412},{"url":"/dataset/syn2real","name":"Syn2Real","full_name":"Syn2Real","num_papers_in_archive":15},{"url":"/dataset/sims4action","name":"Sims4Action","full_name":"","num_papers_in_archive":5},{"url":"/dataset/winsyn","name":"WinSyn","full_name":"WinSyn: A High Resolution Testbed for Synthetic Data","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/image-to-image-translation","name":"Image-to-Image Translation"}],"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":58,"tagged_in_all":68,"items":[{"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/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/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/virtual-to-real-reinforcement-learning-for","title":"Virtual to Real Reinforcement Learning for Autonomous Driving","date":"2017-04-13","arxiv_id":"1704.03952","repositories_listed":6,"syntology":null},{"url":"/paper/advent-adversarial-entropy-minimization-for","title":"ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation","date":"2018-11-30","arxiv_id":"1811.12833","repositories_listed":4,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/daformer-improving-network-architectures-and","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","date":"2021-11-29","arxiv_id":"2111.14887","repositories_listed":3,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":6}},{"url":"/paper/bidirectional-learning-for-domain-adaptation","title":"Bidirectional Learning for Domain Adaptation of Semantic Segmentation","date":"2019-04-24","arxiv_id":"1904.10620","repositories_listed":3,"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/cycada-cycle-consistent-adversarial-domain","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","date":"2017-11-08","arxiv_id":"1711.03213","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/fcns-in-the-wild-pixel-level-adversarial-and","title":"FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation","date":"2016-12-08","arxiv_id":"1612.02649","repositories_listed":3,"syntology":null},{"url":"/paper/transferring-to-real-world-layouts-a-depth","title":"Transferring to Real-World Layouts: A Depth-aware Framework for Scene Adaptation","date":"2023-11-21","arxiv_id":"2311.12682","repositories_listed":2,"syntology":null},{"url":"/paper/adaptive-boosting-for-domain-adaptation","title":"Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation","date":"2021-03-29","arxiv_id":"2103.15685","repositories_listed":2,"syntology":null},{"url":"/paper/prototypical-pseudo-label-denoising-and","title":"Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation","date":"2021-01-26","arxiv_id":"2101.10979","repositories_listed":2,"syntology":{"n":17,"n_ran":8,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/instance-adaptive-self-training-for","title":"Instance Adaptive Self-Training for Unsupervised Domain Adaptation","date":"2020-08-27","arxiv_id":"2008.12197","repositories_listed":2,"syntology":null},{"url":"/paper/dacs-domain-adaptation-via-cross-domain-mixed","title":"DACS: Domain Adaptation via Cross-domain Mixed Sampling","date":"2020-07-17","arxiv_id":"2007.08702","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/unsupervised-intra-domain-adaptation-for","title":"Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision","date":"2020-04-16","arxiv_id":"2004.07703","repositories_listed":2,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/rectifying-pseudo-label-learning-via","title":"Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation","date":"2020-03-08","arxiv_id":"2003.03773","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/confidence-regularized-self-training","title":"Confidence Regularized Self-Training","date":"2019-08-26","arxiv_id":"1908.09822","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/a-curriculum-domain-adaptation-approach-to","title":"A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes","date":"2018-12-24","arxiv_id":"1812.09953","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/learning-content-enhanced-mask-transformer","title":"Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation","date":"2023-07-01","arxiv_id":"2307.00371","repositories_listed":1,"syntology":null},{"url":"/paper/hard-aware-instance-adaptive-self-training","title":"Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation","date":"2023-02-14","arxiv_id":"2302.06992","repositories_listed":1,"syntology":null},{"url":"/paper/mic-masked-image-consistency-for-context","title":"MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation","date":"2022-12-02","arxiv_id":"2212.01322","repositories_listed":1,"syntology":null},{"url":"/paper/elda-using-edges-to-have-an-edge-on-semantic","title":"ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA","date":"2022-11-16","arxiv_id":"2211.08888","repositories_listed":1,"syntology":null},{"url":"/paper/pipa-pixel-and-patch-wise-self-supervised","title":"PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation","date":"2022-11-14","arxiv_id":"2211.07609","repositories_listed":1,"syntology":null},{"url":"/paper/deliberated-domain-bridging-for-domain","title":"Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation","date":"2022-09-16","arxiv_id":"2209.07695","repositories_listed":1,"syntology":null},{"url":"/paper/cluda-contrastive-learning-in-unsupervised","title":"CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation","date":"2022-08-27","arxiv_id":"2208.14227","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-high-quality-target-domain","title":"Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation","date":"2022-08-12","arxiv_id":"2208.06100","repositories_listed":1,"syntology":null},{"url":"/paper/hrda-context-aware-high-resolution-domain","title":"HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation","date":"2022-04-27","arxiv_id":"2204.13132","repositories_listed":1,"syntology":null},{"url":"/paper/procst-boosting-semantic-segmentation-using","title":"ProCST: Boosting Semantic Segmentation Using Progressive Cyclic Style-Transfer","date":"2022-04-25","arxiv_id":"2204.11891","repositories_listed":1,"syntology":null},{"url":"/paper/sepico-semantic-guided-pixel-contrast-for","title":"SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation","date":"2022-04-19","arxiv_id":"2204.08808","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/bidirectional-self-training-with-multiple","title":"Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation","date":"2022-04-16","arxiv_id":"2204.07730","repositories_listed":1,"syntology":null}],"syntology_records":13,"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"}}