{"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/improving-object-detection-with-inverted","title":"Improving Object Detection with Inverted Attention","arxiv_id":"1903.12255","date":"2019-03-28","proceeding":null,"authors":["Zeyi Huang","Wei Ke","Dong Huang"],"abstract":"Improving object detectors against occlusion, blur and noise is a critical\nstep to deploy detectors in real applications. Since it is not possible to\nexhaust all image defects through data collection, many researchers seek to\ngenerate hard samples in training. The generated hard samples are either images\nor feature maps with coarse patches dropped out in the spatial dimensions.\nSignificant overheads are required in training the extra hard samples and/or\nestimating drop-out patches using extra network branches. In this paper, we\nimprove object detectors using a highly efficient and fine-grain mechanism\ncalled Inverted Attention (IA). Different from the original detector network\nthat only focuses on the dominant part of objects, the detector network with IA\niteratively inverts attention on feature maps and puts more attention on\ncomplementary object parts, feature channels and even context. Our approach (1)\noperates along both the spatial and channels dimensions of the feature maps;\n(2) requires no extra training on hard samples, no extra network parameters for\nattention estimation, and no testing overheads. Experiments show that our\napproach consistently improved both two-stage and single-stage detectors on\nbenchmark databases.","url_abs":"http://arxiv.org/abs/1903.12255v1","url_pdf":"http://arxiv.org/pdf/1903.12255v1.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":"improving-object-detection-with-inverted","repo_url":"https://github.com/zichengsaber/Pytorch-Inverted-Attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.12255","atlas_url":"https://app.syntology.ai/?focus=1903.12255","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":"1903.12255"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1903.12255\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1903.12255"},"call":"get_concepts_for_paper(arxiv_id=\"1903.12255\")"}],"by_repo":[{"repo":"zichengsaber/Pytorch-Inverted-Attention","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":"dd3e261824f049f3b6b19486435b1cb223c69b8ef50b8d51e8c94f76738f1d24","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}