{"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/attend-and-rectify-a-gated-attention","title":"Attend and Rectify: a Gated Attention Mechanism for Fine-Grained Recovery","arxiv_id":"1807.07320","date":"2018-07-19","proceeding":"ECCV 2018 9","authors":["Pau Rodríguez","Josep M. Gonfaus","Guillem Cucurull","F. Xavier Roca","Jordi Gonzàlez"],"abstract":"We propose a novel attention mechanism to enhance Convolutional Neural\nNetworks for fine-grained recognition. It learns to attend to lower-level\nfeature activations without requiring part annotations and uses these\nactivations to update and rectify the output likelihood distribution. In\ncontrast to other approaches, the proposed mechanism is modular,\narchitecture-independent and efficient both in terms of parameters and\ncomputation required. Experiments show that networks augmented with our\napproach systematically improve their classification accuracy and become more\nrobust to clutter. As a result, Wide Residual Networks augmented with our\nproposal surpasses the state of the art classification accuracies in CIFAR-10,\nthe Adience gender recognition task, Stanford dogs, and UEC Food-100.","url_abs":"http://arxiv.org/abs/1807.07320v2","url_pdf":"http://arxiv.org/pdf/1807.07320v2.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":"attend-and-rectify-a-gated-attention","repo_url":"https://github.com/prlz77/attend-and-rectify","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"WARN","rank_in_archive_order":108,"of":211,"metrics":{"Percentage correct":"82.18"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.07320","atlas_url":"https://app.syntology.ai/?focus=1807.07320","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":"1807.07320"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1807.07320\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1807.07320"},"call":"get_concepts_for_paper(arxiv_id=\"1807.07320\")"}],"by_repo":[{"repo":"prlz77/attend-and-rectify","kind":"official","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":"85f44b88bc50a438a0ec3a6829465a491848f85bc51a3ce3d5a6d2b9a601c2ab","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}