{"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/semantic-correspondence-with-transformers","title":"CATs: Cost Aggregation Transformers for Visual Correspondence","arxiv_id":"2106.02520","date":"2021-06-04","proceeding":"NeurIPS 2021 12","authors":["Seokju Cho","Sunghwan Hong","Sangryul Jeon","Yunsung Lee","Kwanghoon Sohn","Seungryong Kim"],"abstract":"We propose a novel cost aggregation network, called Cost Aggregation Transformers (CATs), to find dense correspondences between semantically similar images with additional challenges posed by large intra-class appearance and geometric variations. Cost aggregation is a highly important process in matching tasks, which the matching accuracy depends on the quality of its output. Compared to hand-crafted or CNN-based methods addressing the cost aggregation, in that either lacks robustness to severe deformations or inherit the limitation of CNNs that fail to discriminate incorrect matches due to limited receptive fields, CATs explore global consensus among initial correlation map with the help of some architectural designs that allow us to fully leverage self-attention mechanism. Specifically, we include appearance affinity modeling to aid the cost aggregation process in order to disambiguate the noisy initial correlation maps and propose multi-level aggregation to efficiently capture different semantics from hierarchical feature representations. We then combine with swapping self-attention technique and residual connections not only to enforce consistent matching but also to ease the learning process, which we find that these result in an apparent performance boost. We conduct experiments to demonstrate the effectiveness of the proposed model over the latest methods and provide extensive ablation studies. Code and trained models are available at https://github.com/SunghwanHong/CATs.","url_abs":"https://arxiv.org/abs/2106.02520v3","url_pdf":"https://arxiv.org/pdf/2106.02520v3.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":"semantic-correspondence-with-transformers","repo_url":"https://github.com/SunghwanHong/Cost-Aggregation-transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"semantic-correspondence","task_name":"Semantic correspondence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-correspondence-on-pf-pascal","task":"Semantic correspondence","dataset":"PF-PASCAL","model":"CATs","rank_in_archive_order":6,"of":15,"metrics":{"PCK":"92.6"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-correspondence-on-pf-willow","task":"Semantic correspondence","dataset":"PF-WILLOW","model":"CATs","rank_in_archive_order":5,"of":8,"metrics":{"PCK":"79.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-correspondence-on-spair-71k","task":"Semantic correspondence","dataset":"SPair-71k","model":"CATs","rank_in_archive_order":16,"of":22,"metrics":{"PCK":"49.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.02520","atlas_url":"https://app.syntology.ai/?focus=2106.02520","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":"2106.02520"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2106.02520\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2106.02520"},"call":"get_concepts_for_paper(arxiv_id=\"2106.02520\")"}],"by_repo":[{"repo":"SunghwanHong/Cost-Aggregation-transformers","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"1c7e5e50c9e3de4cb5dacdf70bd113cee27c2fa55de351b4b73062e78dbd8770","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}