{"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/hierarchical-attention-network-for-few-shot","title":"Hierarchical Attention Network for Few-Shot Object Detection via Meta-Contrastive Learning","arxiv_id":"2208.07039","date":"2022-08-15","proceeding":null,"authors":["Dongwoo Park","Jong-Min Lee"],"abstract":"Few-shot object detection (FSOD) aims to classify and detect few images of novel categories. Existing meta-learning methods insufficiently exploit features between support and query images owing to structural limitations. We propose a hierarchical attention network with sequentially large receptive fields to fully exploit the query and support images. In addition, meta-learning does not distinguish the categories well because it determines whether the support and query images match. In other words, metric-based learning for classification is ineffective because it does not work directly. Thus, we propose a contrastive learning method called meta-contrastive learning, which directly helps achieve the purpose of the meta-learning strategy. Finally, we establish a new state-of-the-art network, by realizing significant margins. Our method brings 2.3, 1.0, 1.3, 3.4 and 2.4% AP improvements for 1-30 shots object detection on COCO dataset. Our code is available at: https://github.com/infinity7428/hANMCL","url_abs":"https://arxiv.org/abs/2208.07039v3","url_pdf":"https://arxiv.org/pdf/2208.07039v3.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":"hierarchical-attention-network-for-few-shot","repo_url":"https://github.com/infinity7428/hANMCL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-1-shot","task":"Few-Shot Object Detection","dataset":"MS-COCO (1-shot)","model":"hANMCL","rank_in_archive_order":2,"of":7,"metrics":{"AP":"13.4"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-10-shot","task":"Few-Shot Object Detection","dataset":"MS-COCO (10-shot)","model":"hANMCL","rank_in_archive_order":8,"of":33,"metrics":{"AP":"22.4"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-30-shot","task":"Few-Shot Object Detection","dataset":"MS-COCO (30-shot)","model":"hANMCL","rank_in_archive_order":8,"of":25,"metrics":{"AP":"25.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.07039","atlas_url":"https://app.syntology.ai/?focus=2208.07039","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}