{"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/incremental-object-detection-via-meta","title":"Incremental Object Detection via Meta-Learning","arxiv_id":"2003.08798","date":"2020-03-17","proceeding":null,"authors":["K J Joseph","Jathushan Rajasegaran","Salman Khan","Fahad Shahbaz Khan","Vineeth N Balasubramanian"],"abstract":"In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their performance on old classes deteriorates significantly. A few efforts have been reported to address this limitation, all of which apply variants of knowledge distillation to avoid catastrophic forgetting. We note that although distillation helps to retain previous learning, it obstructs fast adaptability to new tasks, which is a critical requirement for incremental learning. In this pursuit, we propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared. This ensures a seamless information transfer via a meta-learned gradient preconditioning that minimizes forgetting and maximizes knowledge transfer. In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection. We evaluate our approach on a variety of incremental learning settings defined on PASCAL-VOC and MS COCO datasets, where our approach performs favourably well against state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2003.08798v3","url_pdf":"https://arxiv.org/pdf/2003.08798v3.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":"incremental-object-detection-via-meta","repo_url":"https://github.com/JosephKJ/iOD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"incremental-object-detection-via-meta","repo_url":"https://github.com/josephkj/eli","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.08798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.08798"}},"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/josephkj/eli","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JosephKJ/iOD","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":9,"samples":[{"code_sha256_prefix":"0df9d3b583fbc6cb","entry":"batched_nms","repo":"JosephKJ/iOD","repo_kind":"official","path":"detectron2/layers/nms.py","file_url":"https://github.com/JosephKJ/iOD/blob/HEAD/detectron2/layers/nms.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0df9d3b583fbc6cb"}},{"code_sha256_prefix":"312f7f3ac838717a","entry":"combine_semantic_and_instance_outputs","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"312f7f3ac838717a"}},{"code_sha256_prefix":"e8526a516b4f9206","entry":"convert_basic_c2_names","repo":"JosephKJ/iOD","repo_kind":"official","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/JosephKJ/iOD/blob/HEAD/detectron2/checkpoint/c2_model_loading.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e8526a516b4f9206"}},{"code_sha256_prefix":"52810b504f0d1066","entry":"convert_c2_detectron_names","repo":"JosephKJ/iOD","repo_kind":"official","path":"detectron2/checkpoint/c2_model_loading.py","file_url":"https://github.com/JosephKJ/iOD/blob/HEAD/detectron2/checkpoint/c2_model_loading.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"52810b504f0d1066"}},{"code_sha256_prefix":"406f84cf799ed34d","entry":"pad_masks","repo":"JosephKJ/iOD","repo_kind":"official","path":"detectron2/layers/mask_ops.py","file_url":"https://github.com/JosephKJ/iOD/blob/HEAD/detectron2/layers/mask_ops.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"406f84cf799ed34d"}},{"code_sha256_prefix":"d03592674030077f","entry":"paste_mask_in_image_old","repo":"JosephKJ/iOD","repo_kind":"official","path":"detectron2/layers/mask_ops.py","file_url":"https://github.com/JosephKJ/iOD/blob/HEAD/detectron2/layers/mask_ops.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d03592674030077f"}},{"code_sha256_prefix":"4845964b76bba6c5","entry":"batched_nms_rotated","repo":"JosephKJ/iOD","repo_kind":"official","path":"detectron2/layers/nms.py","file_url":"https://github.com/JosephKJ/iOD/blob/HEAD/detectron2/layers/nms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4845964b76bba6c5"}},{"code_sha256_prefix":"d3fa37a000ad294d","entry":"nms_rotated","repo":"JosephKJ/iOD","repo_kind":"official","path":"detectron2/layers/nms.py","file_url":"https://github.com/JosephKJ/iOD/blob/HEAD/detectron2/layers/nms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d3fa37a000ad294d"}},{"code_sha256_prefix":"f74abd7e1355f8cd","entry":"paste_masks_in_image","repo":"JosephKJ/iOD","repo_kind":"official","path":"detectron2/layers/mask_ops.py","file_url":"https://github.com/JosephKJ/iOD/blob/HEAD/detectron2/layers/mask_ops.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f74abd7e1355f8cd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}