{"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/democracy-does-matter-comprehensive-feature","title":"Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object Detection","arxiv_id":"2203.05787","date":"2022-03-11","proceeding":"CVPR 2022 1","authors":["Siyue Yu","Jimin Xiao","Bingfeng Zhang","Eng Gee Lim"],"abstract":"Co-salient object detection, with the target of detecting co-existed salient objects among a group of images, is gaining popularity. Recent works use the attention mechanism or extra information to aggregate common co-salient features, leading to incomplete even incorrect responses for target objects. In this paper, we aim to mine comprehensive co-salient features with democracy and reduce background interference without introducing any extra information. To achieve this, we design a democratic prototype generation module to generate democratic response maps, covering sufficient co-salient regions and thereby involving more shared attributes of co-salient objects. Then a comprehensive prototype based on the response maps can be generated as a guide for final prediction. To suppress the noisy background information in the prototype, we propose a self-contrastive learning module, where both positive and negative pairs are formed without relying on additional classification information. Besides, we also design a democratic feature enhancement module to further strengthen the co-salient features by readjusting attention values. Extensive experiments show that our model obtains better performance than previous state-of-the-art methods, especially on challenging real-world cases (e.g., for CoCA, we obtain a gain of 2.0% for MAE, 5.4% for maximum F-measure, 2.3% for maximum E-measure, and 3.7% for S-measure) under the same settings. Code will be released soon.","url_abs":"https://arxiv.org/abs/2203.05787v1","url_pdf":"https://arxiv.org/pdf/2203.05787v1.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":"democracy-does-matter-comprehensive-feature","repo_url":"https://github.com/siyueyu/dcfm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"co-saliency-detection","task_name":"Co-Salient Object Detection"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"mae","method_name":"MAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/co-salient-object-detection-on-coca","task":"Co-Salient Object Detection","dataset":"CoCA","model":"DCFM","rank_in_archive_order":3,"of":10,"metrics":{"MAE":"0.085","Mean F-measure":"0.593","S-measure":"0.710","max E-measure":"0.783","max F-measure":"0.598","mean E-measure":"0.778"},"uses_additional_data":false},{"leaderboard":"/sota/co-salient-object-detection-on-cosod3k","task":"Co-Salient Object Detection","dataset":"CoSOD3k","model":"DCFM","rank_in_archive_order":4,"of":10,"metrics":{"MAE":"0.067","S-measure":"0.809","max E-measure":"0.871","max F-measure":"0.805","mean E-measure":"0.871","mean F-measure":"0.800"},"uses_additional_data":false},{"leaderboard":"/sota/co-salient-object-detection-on-cosal2015","task":"Co-Salient Object Detection","dataset":"CoSal2015","model":"DCFM","rank_in_archive_order":5,"of":10,"metrics":{"MAE":"0.067","S-measure":"0.838","max E-measure":"0.893","max F-measure":"0.856","mean E-measure":"0.889","mean F-measure":"0.850"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.05787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05787"}},"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":"deterministic:regex_extraction","url":"https://github.com/siyueyu/DCFM","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"6e58e4c806892f36","entry":"VGG_Backbone","repo":"siyueyu/DCFM","repo_kind":"official","path":"models/vgg.py","file_url":"https://github.com/siyueyu/DCFM/blob/HEAD/models/vgg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6e58e4c806892f36"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}