{"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/probabilistic-anchor-assignment-with-iou","title":"Probabilistic Anchor Assignment with IoU Prediction for Object Detection","arxiv_id":"2007.08103","date":"2020-07-16","proceeding":"ECCV 2020 8","authors":["Kang Kim","Hee Seok Lee"],"abstract":"In object detection, determining which anchors to assign as positive or negative samples, known as anchor assignment, has been revealed as a core procedure that can significantly affect a model's performance. In this paper we propose a novel anchor assignment strategy that adaptively separates anchors into positive and negative samples for a ground truth bounding box according to the model's learning status such that it is able to reason about the separation in a probabilistic manner. To do so we first calculate the scores of anchors conditioned on the model and fit a probability distribution to these scores. The model is then trained with anchors separated into positive and negative samples according to their probabilities. Moreover, we investigate the gap between the training and testing objectives and propose to predict the Intersection-over-Unions of detected boxes as a measure of localization quality to reduce the discrepancy. The combined score of classification and localization qualities serving as a box selection metric in non-maximum suppression well aligns with the proposed anchor assignment strategy and leads significant performance improvements. The proposed methods only add a single convolutional layer to RetinaNet baseline and does not require multiple anchors per location, so are efficient. Experimental results verify the effectiveness of the proposed methods. Especially, our models set new records for single-stage detectors on MS COCO test-dev dataset with various backbones. Code is available at https://github.com/kkhoot/PAA.","url_abs":"https://arxiv.org/abs/2007.08103v2","url_pdf":"https://arxiv.org/pdf/2007.08103v2.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":"probabilistic-anchor-assignment-with-iou","repo_url":"https://github.com/kkhoot/PAA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"probabilistic-anchor-assignment-with-iou","repo_url":"https://github.com/feiyuhuahuo/PAA_minimal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"probabilistic-anchor-assignment-with-iou","repo_url":"https://github.com/CV51GO/PAA_Megengine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"probabilistic-anchor-assignment-with-iou","repo_url":"https://github.com/kkhoot/PAA_Faster-RCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"probabilistic-anchor-assignment-with-iou","repo_url":"https://github.com/open-mmlab/mmdetection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"focal-loss","method_name":"Focal Loss"},{"method_slug":"probabilistic-anchor-assignment","method_name":"Probabilistic Anchor Assignment"},{"method_slug":"retinanet","method_name":"RetinaNet"}],"datasets_introduced":[],"methods_introduced":[{"slug":"probabilistic-anchor-assignment","name":"Probabilistic Anchor Assignment","full_name":"Probabilistic Anchor Assignment"}],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"PAA (ResNext-152-32x8d + DCN, multi-scale)","rank_in_archive_order":60,"of":225,"metrics":{"AP50":"71.6","AP75":"59.1","APL":"66.9","APM":"56.3","APS":"36.0","box mAP":"53.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.08103","atlas_url":"https://app.syntology.ai/?focus=2007.08103","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":"2007.08103"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2007.08103\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2007.08103"},"call":"get_concepts_for_paper(arxiv_id=\"2007.08103\")"}],"by_repo":[{"repo":"kkhoot/PAA","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"feiyuhuahuo/PAA_minimal","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"CV51GO/PAA_Megengine","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kkhoot/PAA_Faster-RCNN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"open-mmlab/mmdetection","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2401.02361"],"harvested_for_calls":[{"arxiv_id":"2401.02361","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2401.02361"},"call":"get_harvested_code_for_paper(arxiv_id=\"2401.02361\")"}]}],"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":"12c2549b2894da47a38a85faafc44cc61b0c682365c58a5103d3e97691a4ffc9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}