{"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-learning-of-object-detectors","title":"Incremental Learning of Object Detectors without Catastrophic Forgetting","arxiv_id":"1708.06977","date":"2017-08-23","proceeding":"ICCV 2017 10","authors":["Konstantin Shmelkov","Cordelia Schmid","Karteek Alahari"],"abstract":"Despite their success for object detection, convolutional neural networks are\nill-equipped for incremental learning, i.e., adapting the original model\ntrained on a set of classes to additionally detect objects of new classes, in\nthe absence of the initial training data. They suffer from \"catastrophic\nforgetting\" - an abrupt degradation of performance on the original set of\nclasses, when the training objective is adapted to the new classes. We present\na method to address this issue, and learn object detectors incrementally, when\nneither the original training data nor annotations for the original classes in\nthe new training set are available. The core of our proposed solution is a loss\nfunction to balance the interplay between predictions on the new classes and a\nnew distillation loss which minimizes the discrepancy between responses for old\nclasses from the original and the updated networks. This incremental learning\ncan be performed multiple times, for a new set of classes in each step, with a\nmoderate drop in performance compared to the baseline network trained on the\nensemble of data. We present object detection results on the PASCAL VOC 2007\nand COCO datasets, along with a detailed empirical analysis of the approach.","url_abs":"http://arxiv.org/abs/1708.06977v1","url_pdf":"http://arxiv.org/pdf/1708.06977v1.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-learning-of-object-detectors","repo_url":"https://github.com/Ze-Yang/Context-Transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"incremental-learning-of-object-detectors","repo_url":"https://github.com/kshmelkov/incremental_detectors","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"incremental-learning-of-object-detectors","repo_url":"https://github.com/manoja328/rodeo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"incremental-learning","task_name":"Incremental 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":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1708.06977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1708.06977"}},"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/Ze-Yang/Context-Transformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/manoja328/rodeo","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kshmelkov/incremental_detectors","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":"aa3413114f133f9f","entry":"get_logging_config","repo":"kshmelkov/incremental_detectors","repo_kind":"listed","path":"config.py","file_url":"https://github.com/kshmelkov/incremental_detectors/blob/HEAD/config.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"aa3413114f133f9f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}