{"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-dense-correlation-distillation","title":"Hierarchical Dense Correlation Distillation for Few-Shot Segmentation","arxiv_id":"2303.14652","date":"2023-03-26","proceeding":"CVPR 2023 1","authors":["Bohao Peng","Zhuotao Tian","Xiaoyang Wu","Chenyao Wang","Shu Liu","Jingyong Su","Jiaya Jia"],"abstract":"Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic feature and prototype representation suffer from coarse segmentation granularity and train-set overfitting. In this work, we design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. The self-attention modules are used to assist in establishing hierarchical dense features, as a means to accomplish the cascade matching between query and support features. Moreover, we propose a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation. Our method performs decently in experiments. We achieve $50.0\\%$ mIoU on \\coco~dataset one-shot setting and $56.0\\%$ on five-shot segmentation, respectively.","url_abs":"https://arxiv.org/abs/2303.14652v1","url_pdf":"https://arxiv.org/pdf/2303.14652v1.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-dense-correlation-distillation","repo_url":"https://github.com/pbihao/hdmnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"few-shot-image-segmentation","task_name":"Few-Shot Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semantic-correspondence","task_name":"Semantic correspondence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-1","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (1-shot)","model":"HDMNet (ResNet-50)","rank_in_archive_order":11,"of":85,"metrics":{"FB-IoU":"72.2","Mean IoU":"50"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-1","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (1-shot)","model":"HDMNet (VGG-16)","rank_in_archive_order":31,"of":85,"metrics":{"Mean IoU":"45.9"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-5","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (5-shot)","model":"HDMNet (ResNet-50)","rank_in_archive_order":15,"of":81,"metrics":{"FB-IoU":"77.7","Mean IoU":"56"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-5","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (5-shot)","model":"HDMNet (VGG-16)","rank_in_archive_order":27,"of":81,"metrics":{"Mean IoU":"52.4"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i-1","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (1-Shot)","model":"HDMNet (ResNet-50)","rank_in_archive_order":10,"of":105,"metrics":{"Mean IoU":"69.4"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i-1","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (1-Shot)","model":"HDMNet (VGG-16)","rank_in_archive_order":50,"of":105,"metrics":{"Mean IoU":"65.1"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i-5","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (5-Shot)","model":"HDMNet (ResNet-50)","rank_in_archive_order":22,"of":96,"metrics":{"Mean IoU":"71.8"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i-5","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (5-Shot)","model":"HDMNet (VGG-16)","rank_in_archive_order":50,"of":96,"metrics":{"Mean IoU":"69.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.14652","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}