{"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-instance-active-learning-for-object","title":"Multiple instance active learning for object detection","arxiv_id":"2104.02324","date":"2021-04-06","proceeding":"CVPR 2021 1","authors":["Tianning Yuan","Fang Wan","Mengying Fu","Jianzhuang Liu","Songcen Xu","Xiangyang Ji","Qixiang Ye"],"abstract":"Despite the substantial progress of active learning for image recognition, there still lacks an instance-level active learning method specified for object detection. In this paper, we propose Multiple Instance Active Object Detection (MI-AOD), to select the most informative images for detector training by observing instance-level uncertainty. MI-AOD defines an instance uncertainty learning module, which leverages the discrepancy of two adversarial instance classifiers trained on the labeled set to predict instance uncertainty of the unlabeled set. MI-AOD treats unlabeled images as instance bags and feature anchors in images as instances, and estimates the image uncertainty by re-weighting instances in a multiple instance learning (MIL) fashion. Iterative instance uncertainty learning and re-weighting facilitate suppressing noisy instances, toward bridging the gap between instance uncertainty and image-level uncertainty. Experiments validate that MI-AOD sets a solid baseline for instance-level active learning. On commonly used object detection datasets, MI-AOD outperforms state-of-the-art methods with significant margins, particularly when the labeled sets are small. Code is available at https://github.com/yuantn/MI-AOD.","url_abs":"https://arxiv.org/abs/2104.02324v1","url_pdf":"https://arxiv.org/pdf/2104.02324v1.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-instance-active-learning-for-object","repo_url":"https://github.com/yuantn/MI-AOD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"active-object-detection","task_name":"Active Object Detection"},{"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":"non-maximum-suppression","method_name":"Non Maximum Suppression"},{"method_slug":"retinanet","method_name":"RetinaNet"},{"method_slug":"ssd","method_name":"SSD"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/active-object-detection-on-coco","task":"Active Object Detection","dataset":"COCO (Common Objects in Context)","model":"RetinaNet","rank_in_archive_order":1,"of":1,"metrics":{"AP":"(7.3, 13.8, 16.9, 19.1, 20.8) on 2% ~ 10%"},"uses_additional_data":false},{"leaderboard":"/sota/active-object-detection-on-pascal-voc-07-12","task":"Active Object Detection","dataset":"PASCAL VOC 07+12","model":"RetinaNet","rank_in_archive_order":1,"of":2,"metrics":{"mAP":"(47.18, 58.41, 64.02, 67.72, 69.79, 71.07, 72.27) on 5% ~ 20%"},"uses_additional_data":false},{"leaderboard":"/sota/active-object-detection-on-pascal-voc-07-12","task":"Active Object Detection","dataset":"PASCAL VOC 07+12","model":"SSD","rank_in_archive_order":2,"of":2,"metrics":{"mAP":"(53.62, 62.86, 66.83, 69.33, 70.80, 72.21, 72.84, 73.74, 74.18, 74.91) on 1k ~ 10k"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.02324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02324"}},"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":"deterministic:regex_extraction","url":"https://github.com/yuantn/MI-AOD","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"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":"7f548ce1318de33a","entry":"get_X_L_0","repo":"yuantn/MI-AOD","repo_kind":"official","path":"for_coco/active_datasets.py","file_url":"https://github.com/yuantn/MI-AOD/blob/HEAD/for_coco/active_datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7f548ce1318de33a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}