{"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/cfa-constraint-based-finetuning-approach-for","title":"CFA: Constraint-based Finetuning Approach for Generalized Few-Shot Object Detection","arxiv_id":"2204.05220","date":"2022-04-11","proceeding":null,"authors":["Karim Guirguis","Ahmed Hendawy","George Eskandar","Mohamed Abdelsamad","Matthias Kayser","Juergen Beyerer"],"abstract":"Few-shot object detection (FSOD) seeks to detect novel categories with limited data by leveraging prior knowledge from abundant base data. Generalized few-shot object detection (G-FSOD) aims to tackle FSOD without forgetting previously seen base classes and, thus, accounts for a more realistic scenario, where both classes are encountered during test time. While current FSOD methods suffer from catastrophic forgetting, G-FSOD addresses this limitation yet exhibits a performance drop on novel tasks compared to the state-of-the-art FSOD. In this work, we propose a constraint-based finetuning approach (CFA) to alleviate catastrophic forgetting, while achieving competitive results on the novel task without increasing the model capacity. CFA adapts a continual learning method, namely Average Gradient Episodic Memory (A-GEM) to G-FSOD. Specifically, more constraints on the gradient search strategy are imposed from which a new gradient update rule is derived, allowing for better knowledge exchange between base and novel classes. To evaluate our method, we conduct extensive experiments on MS-COCO and PASCAL-VOC datasets. Our method outperforms current FSOD and G-FSOD approaches on the novel task with minor degeneration on the base task. Moreover, CFA is orthogonal to FSOD approaches and operates as a plug-and-play module without increasing the model capacity or inference time.","url_abs":"https://arxiv.org/abs/2204.05220v1","url_pdf":"https://arxiv.org/pdf/2204.05220v1.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":[],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-10-shot","task":"Few-Shot Object Detection","dataset":"MS-COCO (10-shot)","model":"CFA-DeFRCN","rank_in_archive_order":11,"of":33,"metrics":{"AP":"19.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.05220","atlas_url":"https://app.syntology.ai/?focus=2204.05220","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}