{"url":"/dataset/foggy-cityscapes","name":"Foggy Cityscapes","full_name":null,"description_markdown":"**Foggy Cityscapes** is a synthetic foggy dataset which simulates fog on real scenes. Each foggy image is rendered with a clear image and depth map from Cityscapes. Thus the annotations and data split in Foggy Cityscapes are inherited from Cityscapes.\r\n\r\nSource: [Exploring Object Relation in Mean Teacher for Cross-Domain Detection](https://arxiv.org/abs/1904.11245)\r\nImage Source: [http://people.ee.ethz.ch/~csakarid/SFSU_synthetic/](http://people.ee.ethz.ch/~csakarid/SFSU_synthetic/)","description_withheld":null,"homepage":"http://people.ee.ethz.ch/~csakarid/SFSU_synthetic/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/semantic-foggy-scene-understanding-with","title":"Semantic Foggy Scene Understanding with Synthetic Data","first_author":"Christos Sakaridis","url":null},"license":{"name":"Custom","url":"http://people.ee.ethz.ch/~csakarid/SFSU_synthetic/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Domain Adaptation","url":"/task/domain-adaptation","datasets_with_task":"/datasets/task/domain-adaptation"},{"name":"Image-to-Image Translation","url":"/task/image-to-image-translation","datasets_with_task":"/datasets/task/image-to-image-translation"},{"name":"Unsupervised Domain Adaptation","url":"/task/unsupervised-domain-adaptation","datasets_with_task":"/datasets/task/unsupervised-domain-adaptation"},{"name":"Weakly Supervised Object Detection","url":"/task/weakly-supervised-object-detection","datasets_with_task":"/datasets/task/weakly-supervised-object-detection"},{"name":"Foggy Scene Segmentation","url":"/task/foggy-scene-segmentation","datasets_with_task":"/datasets/task/foggy-scene-segmentation"},{"name":"Source Free Object Detection","url":"/task/source-free-object-detection","datasets_with_task":"/datasets/task/source-free-object-detection"}],"languages":[],"variants":["Cityscapes to Foggy Cityscapes","Cityscapes-to-Foggy Cityscapes","Foggy Cityscapes"],"data_loaders":[],"num_papers_in_archive":249,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/unsupervised-domain-adaptation-on-cityscapes-1","task":"Unsupervised Domain Adaptation","dataset_variant":"Cityscapes to Foggy Cityscapes","rows":22,"metrics":["mAP@0.5"],"first_row_in_archive_order":{"model":"ALDI++(Resnet50+FPN)","paper":null,"metrics":{"mAP@0.5":"66.8"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/source-free-object-detection-on-cityscapes-to","task":"Source Free Object Detection","dataset_variant":"Cityscapes to Foggy Cityscapes","rows":13,"metrics":["AP50"],"first_row_in_archive_order":{"model":"GT","paper":"/paper/context-aware-grounded-teacher-for-source-1","metrics":{"AP50":"50.8"},"code_links":[{"title":"Tajamul21/Grounded_Teacher","url":"https://github.com/Tajamul21/Grounded_Teacher"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-to-image-translation-on-cityscapes-to","task":"Image-to-Image Translation","dataset_variant":"Cityscapes-to-Foggy Cityscapes","rows":6,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MIC","paper":"/paper/mic-masked-image-consistency-for-context","metrics":{"mAP":"47.6"},"code_links":[{"title":"lhoyer/mic","url":"https://github.com/lhoyer/mic"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/weakly-supervised-object-detection-on-6","task":"Weakly Supervised Object Detection","dataset_variant":"Cityscapes-to-Foggy Cityscapes","rows":2,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MEAA","paper":"/paper/domain-adaptive-object-detection-via-1","metrics":{"mAP":"40.5"},"code_links":[{"title":"basiclab/DA-OD-MEAA-PyTorch","url":"https://github.com/basiclab/DA-OD-MEAA-PyTorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/domain-adaptation-on-foggy-cityscapes","task":"Domain Adaptation","dataset_variant":"Foggy Cityscapes","rows":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"MILA","paper":"/paper/mila-memory-based-instance-level-adaptation-1","metrics":{"mAP":"50.6"},"code_links":[{"title":"hitachi-rd-cv/MILA","url":"https://github.com/hitachi-rd-cv/MILA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/foggy-scene-segmentation-on-foggy-cityscapes","task":"Foggy Scene Segmentation","dataset_variant":"Foggy Cityscapes","rows":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"BWG","paper":"/paper/learning-generalized-segmentation-for-foggy","metrics":{"mIoU":"77.4"},"code_links":[{"title":"BiQiWHU/BWG","url":"https://github.com/BiQiWHU/BWG"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/object-detection-on-cityscapes-to-foggy","task":"Object Detection","dataset_variant":"Cityscapes to Foggy Cityscapes","rows":1,"metrics":["mAP"],"first_row_in_archive_order":{"model":"CDDMSL","paper":"/paper/semi-supervised-domain-generalization-for-1","metrics":{"mAP":"54.3"},"code_links":[{"title":"sinamalakouti/CDDMSL","url":"https://github.com/sinamalakouti/CDDMSL"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/diffusion-domain-teacher-diffusion-guided","title":"Diffusion Domain Teacher: Diffusion Guided Domain Adaptive Object Detector","date":"2025-06-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/context-aware-grounded-teacher-for-source-1","title":"Context Aware Grounded Teacher for Source Free Object Detection","date":"2025-04-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rt-datr-real-time-unsupervised-domain","title":"RT-DATR:Real-time Unsupervised Domain Adaptive Detection Transformer with Adversarial Feature Learning","date":"2025-04-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/improving-object-detection-via-local-global","title":"Improving Object Detection via Local-global Contrastive Learning","date":"2024-10-07","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/enhancing-source-free-domain-adaptive-object","title":"Enhancing Source-Free Domain Adaptive Object Detection with Low-confidence Pseudo Label Distillation","date":"2024-07-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/simplifying-source-free-domain-adaptation-for","title":"Simplifying Source-Free Domain Adaptation for Object Detection: Effective Self-Training Strategies and Performance Insights","date":"2024-07-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/align-and-distill-unifying-and-improving","title":"Align and Distill: Unifying and Improving Domain Adaptive Object Detection","date":"2024-03-18","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/learning-generalized-segmentation-for-foggy","title":"Learning Generalized Segmentation for Foggy-scenes by Bi-directional Wavelet Guidance","date":"2024-02-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-source-free-domain-adaptation-via","title":"Multi-source-free Domain Adaptation via Uncertainty-aware Adaptive Distillation","date":"2024-02-09","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/periodically-exchange-teacher-student-for-1","title":"Periodically Exchange Teacher-Student for Source-Free Object Detection","date":"2023-11-23","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/exploiting-low-confidence-pseudo-labels-for","title":"Exploiting Low-confidence Pseudo-labels for Source-free Object Detection","date":"2023-10-19","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-domain-generalization-for-1","title":"Semi-Supervised Domain Generalization for Object Detection via Language-Guided Feature Alignment","date":"2023-09-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mila-memory-based-instance-level-adaptation-1","title":"MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection","date":"2023-09-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adversarial-alignment-for-source-free-object","title":"Adversarial Alignment for Source Free Object Detection","date":"2023-01-11","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/masked-retraining-teacher-student-framework","title":"Masked Retraining Teacher-Student Framework for Domain Adaptive Object Detection","date":"2023-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mic-masked-image-consistency-for-context","title":"MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation","date":"2022-12-02","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/awada-attention-weighted-adversarial-domain","title":"AWADA: Attention-Weighted Adversarial Domain Adaptation for Object Detection","date":"2022-08-31","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-transferability-for-domain-adaptive","title":"Improving Transferability for Domain Adaptive Detection Transformers","date":"2022-04-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/instance-relation-graph-guided-source-free","title":"Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection","date":"2022-03-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/decompose-to-adapt-cross-domain-object","title":"Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement","date":"2022-01-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":1,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/to-miss-attend-is-to-misalign-residual-self","title":"To miss-attend is to misalign! Residual Self-Attentive Feature Alignment for Adapting Object Detectors","date":"2022-01-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/source-free-object-detection-by-learning-to","title":"Source-Free Object Detection by Learning To Overlook Domain Style","date":"2022-01-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/model-adaptation-historical-contrastive","title":"Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data","date":"2021-10-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/seeking-similarities-over-differences","title":"Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection","date":"2021-10-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/self-adversarial-disentangling-for-specific","title":"Self-Adversarial Disentangling for Specific Domain Adaptation","date":"2021-08-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-free-lunch-for-unsupervised-domain-adaptive","title":"A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data","date":"2020-12-10","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/bi-dimensional-feature-alignment-for-cross","title":"Bi-Dimensional Feature Alignment for Cross-Domain Object Detection","date":"2020-11-14","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/domain-adaptive-object-detection-via-1","title":"Domain-Adaptive Object Detection via Uncertainty-Aware Distribution Alignment","date":"2020-10-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/synthetic-to-real-unsupervised-domain","title":"An Unsupervised Domain Adaptation Scheme for Single-Stage Artwork Recognition in Cultural Sites","date":"2020-08-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/spatial-attention-pyramid-network-for","title":"Spatial Attention Pyramid Network for Unsupervised Domain Adaptation","date":"2020-03-29","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/adaptive-object-detection-with-dual-multi","title":"Adaptive Object Detection with Dual Multi-Label Prediction","date":"2020-03-29","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/harmonizing-transferability-and","title":"Harmonizing Transferability and Discriminability for Adapting Object Detectors","date":"2020-03-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/progressive-domain-adaptation-for-object","title":"Progressive Domain Adaptation for Object Detection","date":"2019-10-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":0,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adapting-object-detectors-via-selective-cross","title":"Adapting Object Detectors via Selective Cross-Domain Alignment","date":"2019-06-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/diversify-and-match-a-domain-adaptive","title":"Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection","date":"2019-05-14","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/strong-weak-distribution-alignment-for","title":"Strong-Weak Distribution Alignment for Adaptive Object Detection","date":"2018-12-12","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/domain-adaptive-faster-r-cnn-for-object","title":"Domain Adaptive Faster R-CNN for Object Detection in the Wild","date":"2018-03-08","rows_on_this_dataset":2,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":1,"samples_unverified":7,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mean-teachers-are-better-role-models-weight","title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","date":"2017-03-06","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":33,"samples_ran":8,"samples_unverified":25,"pointer_only_for_licence":10,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}