{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/multi-evidence-filtering-and-fusion-for-multi","title":"Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning","arxiv_id":"1802.09129","date":"2018-02-26","proceeding":"CVPR 2018 6","authors":["Weifeng Ge","Sibei Yang","Yizhou Yu"],"abstract":"Supervised object detection and semantic segmentation require object or even\npixel level annotations. When there exist image level labels only, it is\nchallenging for weakly supervised algorithms to achieve accurate predictions.\nThe accuracy achieved by top weakly supervised algorithms is still\nsignificantly lower than their fully supervised counterparts. In this paper, we\npropose a novel weakly supervised curriculum learning pipeline for multi-label\nobject recognition, detection and semantic segmentation. In this pipeline, we\nfirst obtain intermediate object localization and pixel labeling results for\nthe training images, and then use such results to train task-specific deep\nnetworks in a fully supervised manner. The entire process consists of four\nstages, including object localization in the training images, filtering and\nfusing object instances, pixel labeling for the training images, and\ntask-specific network training. To obtain clean object instances in the\ntraining images, we propose a novel algorithm for filtering, fusing and\nclassifying object instances collected from multiple solution mechanisms. In\nthis algorithm, we incorporate both metric learning and density-based\nclustering to filter detected object instances. Experiments show that our\nweakly supervised pipeline achieves state-of-the-art results in multi-label\nimage classification as well as weakly supervised object detection and very\ncompetitive results in weakly supervised semantic segmentation on MS-COCO,\nPASCAL VOC 2007 and PASCAL VOC 2012.","url_abs":"http://arxiv.org/abs/1802.09129v1","url_pdf":"http://arxiv.org/pdf/1802.09129v1.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":"clustering","task_name":"Clustering"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"multi-label-classification-2","task_name":"MUlTI-LABEL-ClASSIFICATION"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"multi-label-classification","task_name":"Multi-Label Classification"},{"task_slug":"multi-label-image-classification","task_name":"Multi-Label Image Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-localization","task_name":"Object Localization"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"weakly-supervised-object-detection","task_name":"Weakly Supervised Object Detection"},{"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"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/weakly-supervised-object-detection-on-pascal-1","task":"Weakly Supervised Object Detection","dataset":"PASCAL VOC 2007","model":"pipeline method","rank_in_archive_order":21,"of":41,"metrics":{"MAP":"51.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.09129","atlas_url":"https://app.syntology.ai/?focus=1802.09129","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1802.09129"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1802.09129\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1802.09129"},"call":"get_concepts_for_paper(arxiv_id=\"1802.09129\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"586fa754404ced713393ee5b883b0d83194c89c7e4c5e5418da40c1c68e025ca","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}