{"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/puzzle-cam-improved-localization-via-matching","title":"Puzzle-CAM: Improved localization via matching partial and full features","arxiv_id":"2101.11253","date":"2021-01-27","proceeding":null,"authors":["Sanghyun Jo","In-Jae Yu"],"abstract":"Weakly-supervised semantic segmentation (WSSS) is introduced to narrow the gap for semantic segmentation performance from pixel-level supervision to image-level supervision. Most advanced approaches are based on class activation maps (CAMs) to generate pseudo-labels to train the segmentation network. The main limitation of WSSS is that the process of generating pseudo-labels from CAMs that use an image classifier is mainly focused on the most discriminative parts of the objects. To address this issue, we propose Puzzle-CAM, a process that minimizes differences between the features from separate patches and the whole image. Our method consists of a puzzle module and two regularization terms to discover the most integrated region in an object. Puzzle-CAM can activate the overall region of an object using image-level supervision without requiring extra parameters. % In experiments, Puzzle-CAM outperformed previous state-of-the-art methods using the same labels for supervision on the PASCAL VOC 2012 test dataset. In experiments, Puzzle-CAM outperformed previous state-of-the-art methods using the same labels for supervision on the PASCAL VOC 2012 dataset. Code associated with our experiments is available at https://github.com/OFRIN/PuzzleCAM.","url_abs":"https://arxiv.org/abs/2101.11253v4","url_pdf":"https://arxiv.org/pdf/2101.11253v4.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":"puzzle-cam-improved-localization-via-matching","repo_url":"https://github.com/OFRIN/PuzzleCAM","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"puzzle-cam-improved-localization-via-matching","repo_url":"https://github.com/altimerk/stanford_drone_segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"puzzle-cam-improved-localization-via-matching","repo_url":"https://github.com/dbash/zerowaste","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"puzzle-cam-improved-localization-via-matching","repo_url":"https://github.com/shjo-april/puzzlecam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation-1","task_name":"Weakly supervised Semantic Segmentation"},{"task_slug":"weakly-supervised-semantic-segmentation","task_name":"Weakly-Supervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"Puzzle-CAM (ResNeSt-269)","rank_in_archive_order":22,"of":60,"metrics":{"Mean IoU":"72.2"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on-1","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 test","model":"Puzzle-CAM (ResNeSt-101)","rank_in_archive_order":55,"of":60,"metrics":{"Mean IoU":"67.7"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"Puzzle-CAM (ResNeSt-269)","rank_in_archive_order":22,"of":73,"metrics":{"Mean IoU":"71.9"},"uses_additional_data":false},{"leaderboard":"/sota/weakly-supervised-semantic-segmentation-on","task":"Weakly-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 val","model":"Puzzle-CAM (ResNeSt-101)","rank_in_archive_order":64,"of":73,"metrics":{"Mean IoU":"66.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2101.11253","atlas_url":"https://app.syntology.ai/?focus=2101.11253","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}