{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/bending-reality-distortion-aware-transformers","title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","arxiv_id":"2203.01452","date":"2022-03-02","proceeding":"CVPR 2022 1","authors":["Jiaming Zhang","Kailun Yang","Chaoxiang Ma","Simon Reiß","Kunyu Peng","Rainer Stiefelhagen"],"abstract":"Panoramic images with their 360-degree directional view encompass exhaustive information about the surrounding space, providing a rich foundation for scene understanding. To unfold this potential in the form of robust panoramic segmentation models, large quantities of expensive, pixel-wise annotations are crucial for success. Such annotations are available, but predominantly for narrow-angle, pinhole-camera images which, off the shelf, serve as sub-optimal resources for training panoramic models. Distortions and the distinct image-feature distribution in 360-degree panoramas impede the transfer from the annotation-rich pinhole domain and therefore come with a big dent in performance. To get around this domain difference and bring together semantic annotations from pinhole- and 360-degree surround-visuals, we propose to learn object deformations and panoramic image distortions in the Deformable Patch Embedding (DPE) and Deformable MLP (DMLP) components which blend into our Transformer for PAnoramic Semantic Segmentation (Trans4PASS) model. Finally, we tie together shared semantics in pinhole- and panoramic feature embeddings by generating multi-scale prototype features and aligning them in our Mutual Prototypical Adaptation (MPA) for unsupervised domain adaptation. On the indoor Stanford2D3D dataset, our Trans4PASS with MPA maintains comparable performance to fully-supervised state-of-the-arts, cutting the need for over 1,400 labeled panoramas. On the outdoor DensePASS dataset, we break state-of-the-art by 14.39% mIoU and set the new bar at 56.38%. Code will be made publicly available at https://github.com/jamycheung/Trans4PASS.","url_abs":"https://arxiv.org/abs/2203.01452v2","url_pdf":"https://arxiv.org/pdf/2203.01452v2.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":"bending-reality-distortion-aware-transformers","repo_url":"https://github.com/jamycheung/trans4pass","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"Trans4PASS (Small)","rank_in_archive_order":46,"of":99,"metrics":{"mIoU":"81.1%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"Trans4PASS (Tiny)","rank_in_archive_order":58,"of":99,"metrics":{"mIoU":"79.1%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-densepass","task":"Semantic Segmentation","dataset":"DensePASS","model":"Trans4PASS (multi-scale)","rank_in_archive_order":3,"of":36,"metrics":{"mIoU":"56.38%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-densepass","task":"Semantic Segmentation","dataset":"DensePASS","model":"Trans4PASS (single-scale)","rank_in_archive_order":4,"of":36,"metrics":{"mIoU":"55.25%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-stanford2d3d-1","task":"Semantic Segmentation","dataset":"Stanford2D3D Panoramic","model":"Trans4PASS (Supervised + Small + MS)","rank_in_archive_order":8,"of":25,"metrics":{"mIoU":"53.0%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-stanford2d3d-1","task":"Semantic Segmentation","dataset":"Stanford2D3D Panoramic","model":"Trans4PASS (Supervised + Small)","rank_in_archive_order":12,"of":25,"metrics":{"mIoU":"52.1%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-stanford2d3d-1","task":"Semantic Segmentation","dataset":"Stanford2D3D Panoramic","model":"Trans4PASS (UDA + MPA + MS)","rank_in_archive_order":14,"of":25,"metrics":{"mIoU":"51.2%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-stanford2d3d-1","task":"Semantic Segmentation","dataset":"Stanford2D3D Panoramic","model":"Trans4PASS (UDA + MPA)","rank_in_archive_order":15,"of":25,"metrics":{"mIoU":"50.8%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-stanford2d3d-1","task":"Semantic Segmentation","dataset":"Stanford2D3D Panoramic","model":"Trans4PASS (UDA + Source Only)","rank_in_archive_order":17,"of":25,"metrics":{"mIoU":"48.1%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-synpass","task":"Semantic Segmentation","dataset":"SynPASS","model":"Trans4PASS","rank_in_archive_order":2,"of":6,"metrics":{"mIoU":"38.57%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.01452","atlas_url":"https://app.syntology.ai/?focus=2203.01452","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2203.01452"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2203.01452\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2203.01452"},"call":"get_concepts_for_paper(arxiv_id=\"2203.01452\")"}],"by_repo":[{"repo":"jamycheung/trans4pass","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1702.01105"],"harvested_for_calls":[{"arxiv_id":"1702.01105","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1702.01105"},"call":"get_harvested_code_for_paper(arxiv_id=\"1702.01105\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"39ddf496df3ef1483aaf37abac271d3ecf33448d64f9ac306c73d3fa13fa77d6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}