{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/multiple-anchor-learning-for-visual-object","title":"Multiple Anchor Learning for Visual Object Detection","arxiv_id":"1912.02252","date":"2019-12-04","proceeding":"CVPR 2020 6","authors":["Wei Ke","Tianliang Zhang","Zeyi Huang","Qixiang Ye","Jianzhuang Liu","Dong Huang"],"abstract":"Classification and localization are two pillars of visual object detectors. However, in CNN-based detectors, these two modules are usually optimized under a fixed set of candidate (or anchor) bounding boxes. This configuration significantly limits the possibility to jointly optimize classification and localization. In this paper, we propose a Multiple Instance Learning (MIL) approach that selects anchors and jointly optimizes the two modules of a CNN-based object detector. Our approach, referred to as Multiple Anchor Learning (MAL), constructs anchor bags and selects the most representative anchors from each bag. Such an iterative selection process is potentially NP-hard to optimize. To address this issue, we solve MAL by repetitively depressing the confidence of selected anchors by perturbing their corresponding features. In an adversarial selection-depression manner, MAL not only pursues optimal solutions but also fully leverages multiple anchors/features to learn a detection model. Experiments show that MAL improves the baseline RetinaNet with significant margins on the commonly used MS-COCO object detection benchmark and achieves new state-of-the-art detection performance compared with recent methods.","url_abs":"https://arxiv.org/abs/1912.02252v1","url_pdf":"https://arxiv.org/pdf/1912.02252v1.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":"multiple-anchor-learning-for-visual-object","repo_url":"https://github.com/KevinKecc/MAL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multiple-anchor-learning-for-visual-object","repo_url":"https://github.com/DeLightCMU/MAL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multiple-anchor-learning-for-visual-object","repo_url":"https://github.com/DeLightCMU/MAL-inference","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multiple-instance-learning","task_name":"Multiple Instance Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"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":"retinanet","method_name":"RetinaNet"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"MAL (ResNeXt101, multi-scale)","rank_in_archive_order":122,"of":225,"metrics":{"box mAP":"47.0"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"MAL (ResNeXt101, single-scale)","rank_in_archive_order":135,"of":225,"metrics":{"box mAP":"45.9"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-coco","task":"Object Detection","dataset":"COCO test-dev","model":"MAL (ResNet50, single-scale)","rank_in_archive_order":207,"of":225,"metrics":{"box mAP":"39.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.02252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02252"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KevinKecc/MAL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DeLightCMU/MAL","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DeLightCMU/MAL-inference","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"ran":1,"unverified":9},"by_repo_kind":{"listed":{"samples":10,"ran":1,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e261fa29066b37e5","entry":"smooth_l1_loss","repo":"DeLightCMU/MAL","repo_kind":"listed","path":"maskrcnn_benchmark/layers/smooth_l1_loss.py","file_url":"https://github.com/DeLightCMU/MAL/blob/HEAD/maskrcnn_benchmark/layers/smooth_l1_loss.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e261fa29066b37e5"}},{"code_sha256_prefix":"6693e538e48a84c9","entry":"box2delta","repo":"DeLightCMU/MAL-inference","repo_kind":"listed","path":"retinanet/box.py","file_url":"https://github.com/DeLightCMU/MAL-inference/blob/HEAD/retinanet/box.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6693e538e48a84c9"}},{"code_sha256_prefix":"661727cf46a893a5","entry":"build_resnet_backbone","repo":"DeLightCMU/MAL-inference","repo_kind":"listed","path":"retinanet/backbones/backbone.py","file_url":"https://github.com/DeLightCMU/MAL-inference/blob/HEAD/retinanet/backbones/backbone.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"661727cf46a893a5"}},{"code_sha256_prefix":"b8551d861a720f33","entry":"build_resnet_fpn_backbone","repo":"DeLightCMU/MAL-inference","repo_kind":"listed","path":"retinanet/backbones/backbone.py","file_url":"https://github.com/DeLightCMU/MAL-inference/blob/HEAD/retinanet/backbones/backbone.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b8551d861a720f33"}},{"code_sha256_prefix":"81c87c9068bdbd50","entry":"build_resnet_fpn_p3p7_backbone","repo":"DeLightCMU/MAL-inference","repo_kind":"listed","path":"retinanet/backbones/backbone.py","file_url":"https://github.com/DeLightCMU/MAL-inference/blob/HEAD/retinanet/backbones/backbone.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"81c87c9068bdbd50"}},{"code_sha256_prefix":"333799a2d6f1a170","entry":"convert_fixedbn_model","repo":"DeLightCMU/MAL-inference","repo_kind":"listed","path":"retinanet/backbones/layers.py","file_url":"https://github.com/DeLightCMU/MAL-inference/blob/HEAD/retinanet/backbones/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"333799a2d6f1a170"}},{"code_sha256_prefix":"7e0127e0e305eb71","entry":"delta2box1","repo":"DeLightCMU/MAL-inference","repo_kind":"listed","path":"retinanet/box.py","file_url":"https://github.com/DeLightCMU/MAL-inference/blob/HEAD/retinanet/box.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7e0127e0e305eb71"}},{"code_sha256_prefix":"df48fc695a8a624c","entry":"generate_anchors","repo":"DeLightCMU/MAL-inference","repo_kind":"listed","path":"retinanet/box.py","file_url":"https://github.com/DeLightCMU/MAL-inference/blob/HEAD/retinanet/box.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"df48fc695a8a624c"}},{"code_sha256_prefix":"2902bf4410253ff7","entry":"interpolate","repo":"DeLightCMU/MAL","repo_kind":"listed","path":"maskrcnn_benchmark/layers/misc.py","file_url":"https://github.com/DeLightCMU/MAL/blob/HEAD/maskrcnn_benchmark/layers/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2902bf4410253ff7"}},{"code_sha256_prefix":"deef1b581ac0b1ec","entry":"show_detections","repo":"DeLightCMU/MAL-inference","repo_kind":"listed","path":"retinanet/utils.py","file_url":"https://github.com/DeLightCMU/MAL-inference/blob/HEAD/retinanet/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"deef1b581ac0b1ec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}