{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/style-hallucinated-dual-consistency-learning","title":"Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation","arxiv_id":"2204.02548","date":"2022-04-06","proceeding":null,"authors":["Yuyang Zhao","Zhun Zhong","Na Zhao","Nicu Sebe","Gim Hee Lee"],"abstract":"In this paper, we study the task of synthetic-to-real domain generalized semantic segmentation, which aims to learn a model that is robust to unseen real-world scenes using only synthetic data. The large domain shift between synthetic and real-world data, including the limited source environmental variations and the large distribution gap between synthetic and real-world data, significantly hinders the model performance on unseen real-world scenes. In this work, we propose the Style-HAllucinated Dual consistEncy learning (SHADE) framework to handle such domain shift. Specifically, SHADE is constructed based on two consistency constraints, Style Consistency (SC) and Retrospection Consistency (RC). SC enriches the source situations and encourages the model to learn consistent representation across style-diversified samples. RC leverages real-world knowledge to prevent the model from overfitting to synthetic data and thus largely keeps the representation consistent between the synthetic and real-world models. Furthermore, we present a novel style hallucination module (SHM) to generate style-diversified samples that are essential to consistency learning. SHM selects basis styles from the source distribution, enabling the model to dynamically generate diverse and realistic samples during training. Experiments show that our SHADE yields significant improvement and outperforms state-of-the-art methods by 5.05% and 8.35% on the average mIoU of three real-world datasets on single- and multi-source settings, respectively.","url_abs":"https://arxiv.org/abs/2204.02548v2","url_pdf":"https://arxiv.org/pdf/2204.02548v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"style-hallucinated-dual-consistency-learning","repo_url":"https://github.com/helioszhao/shade","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"style-hallucinated-dual-consistency-learning","repo_url":"https://github.com/helioszhao/shade-visualdg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"robust-object-detection","task_name":"Robust Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"world-knowledge","task_name":"World Knowledge"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-gta-to-avg","task":"Domain Generalization","dataset":"GTA-to-Avg(Cityscapes,BDD,Mapillary)","model":"SHADE","rank_in_archive_order":16,"of":24,"metrics":{"mIoU":"45.27"},"uses_additional_data":false},{"leaderboard":"/sota/robust-object-detection-on-dwd","task":"Robust Object Detection","dataset":"DWD","model":"SHADE","rank_in_archive_order":8,"of":12,"metrics":{"mPC [AP50]":"28.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.02548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02548"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/helioszhao/shade-visualdg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/helioszhao/shade","reach":null}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"b5bf1b24fa41f5c7","entry":"StyleHallucination","repo":"helioszhao/shade-visualdg","repo_kind":"listed","path":"imcls/models/style_hallucination.py","file_url":"https://github.com/helioszhao/shade-visualdg/blob/HEAD/imcls/models/style_hallucination.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5bf1b24fa41f5c7"}},{"code_sha256_prefix":"b3532d08c4680854","entry":"StyleHallucination","repo":"helioszhao/shade","repo_kind":"official","path":"network/style_hallucination.py","file_url":"https://github.com/helioszhao/shade/blob/HEAD/network/style_hallucination.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b3532d08c4680854"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}