{"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/toward-unsupervised-multi-object-discovery-in","title":"Toward unsupervised, multi-object discovery in large-scale image collections","arxiv_id":"2007.02662","date":"2020-07-06","proceeding":"ECCV 2020 8","authors":["Huy V. Vo","Patrick Pérez","Jean Ponce"],"abstract":"This paper addresses the problem of discovering the objects present in a collection of images without any supervision. We build on the optimization approach of Vo et al. (CVPR'19) with several key novelties: (1) We propose a novel saliency-based region proposal algorithm that achieves significantly higher overlap with ground-truth objects than other competitive methods. This procedure leverages off-the-shelf CNN features trained on classification tasks without any bounding box information, but is otherwise unsupervised. (2) We exploit the inherent hierarchical structure of proposals as an effective regularizer for the approach to object discovery of Vo et al., boosting its performance to significantly improve over the state of the art on several standard benchmarks. (3) We adopt a two-stage strategy to select promising proposals using small random sets of images before using the whole image collection to discover the objects it depicts, allowing us to tackle, for the first time (to the best of our knowledge), the discovery of multiple objects in each one of the pictures making up datasets with up to 20,000 images, an over five-fold increase compared to existing methods, and a first step toward true large-scale unsupervised image interpretation.","url_abs":"https://arxiv.org/abs/2007.02662v2","url_pdf":"https://arxiv.org/pdf/2007.02662v2.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":"toward-unsupervised-multi-object-discovery-in","repo_url":"https://github.com/huyvvo/rOSD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"multi-object-colocalization","task_name":"Multi-object colocalization"},{"task_slug":"multi-object-discovery","task_name":"Multi-object discovery"},{"task_slug":"object-discovery","task_name":"Object Discovery"},{"task_slug":"region-proposal","task_name":"Region Proposal"},{"task_slug":"single-object-colocalization","task_name":"Single-object colocalization"},{"task_slug":"single-object-discovery","task_name":"Single-object discovery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-object-colocalization-on-voc12","task":"Multi-object colocalization","dataset":"VOC12","model":"rOSD","rank_in_archive_order":1,"of":1,"metrics":{"Detection Rate":"51.5"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-colocalization-on-voc-all","task":"Multi-object colocalization","dataset":"VOC_all","model":"rOSD","rank_in_archive_order":1,"of":1,"metrics":{"Detection Rate":"49.4"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-discovery-on-coco-20k","task":"Multi-object discovery","dataset":"COCO_20k","model":"Large-scale rOSD","rank_in_archive_order":1,"of":1,"metrics":{"Detection Rate":"12.0"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-discovery-on-voc12","task":"Multi-object discovery","dataset":"VOC12","model":"Large-scale rOSD","rank_in_archive_order":1,"of":2,"metrics":{"Detection Rate":"41.2"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-discovery-on-voc12","task":"Multi-object discovery","dataset":"VOC12","model":"rOSD","rank_in_archive_order":2,"of":2,"metrics":{"Detection Rate":"40.4"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-discovery-on-voc-all","task":"Multi-object discovery","dataset":"VOC_all","model":"Large-scale rOSD","rank_in_archive_order":1,"of":2,"metrics":{"Detection Rate":"38.3"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-discovery-on-voc-all","task":"Multi-object discovery","dataset":"VOC_all","model":"rOSD","rank_in_archive_order":2,"of":2,"metrics":{"Detection Rate":"37.6"},"uses_additional_data":false},{"leaderboard":"/sota/single-object-discovery-on-coco-20k","task":"Single-object discovery","dataset":"COCO_20k","model":"rOSD + CAD","rank_in_archive_order":7,"of":10,"metrics":{"CorLoc":"53.0"},"uses_additional_data":false},{"leaderboard":"/sota/single-object-discovery-on-coco-20k","task":"Single-object discovery","dataset":"COCO_20k","model":"rOSD","rank_in_archive_order":9,"of":10,"metrics":{"CorLoc":"48.5"},"uses_additional_data":false},{"leaderboard":"/sota/single-object-discovery-on-object-discovery","task":"Single-object discovery","dataset":"Object Discovery","model":"rOSD","rank_in_archive_order":1,"of":2,"metrics":{"CorLoc":"89.2"},"uses_additional_data":false},{"leaderboard":"/sota/single-object-discovery-on-voc12","task":"Single-object discovery","dataset":"VOC12","model":"Large-scale rOSD","rank_in_archive_order":1,"of":2,"metrics":{"CorLoc":"51.9"},"uses_additional_data":false},{"leaderboard":"/sota/single-object-discovery-on-voc12","task":"Single-object discovery","dataset":"VOC12","model":"rOSD","rank_in_archive_order":2,"of":2,"metrics":{"CorLoc":"51.2"},"uses_additional_data":false},{"leaderboard":"/sota/single-object-discovery-on-voc-6x2","task":"Single-object discovery","dataset":"VOC_6x2","model":"rOSD","rank_in_archive_order":1,"of":2,"metrics":{"CorLoc":"72.5"},"uses_additional_data":false},{"leaderboard":"/sota/single-object-discovery-on-voc-all","task":"Single-object discovery","dataset":"VOC_all","model":"Large-scale rOSD","rank_in_archive_order":1,"of":3,"metrics":{"CorLoc":"49.4"},"uses_additional_data":false},{"leaderboard":"/sota/single-object-discovery-on-voc-all","task":"Single-object discovery","dataset":"VOC_all","model":"rOSD","rank_in_archive_order":2,"of":3,"metrics":{"CorLoc":"49.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2007.02662","atlas_url":"https://app.syntology.ai/?focus=2007.02662","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":"2007.02662"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2007.02662\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2007.02662"},"call":"get_concepts_for_paper(arxiv_id=\"2007.02662\")"}],"by_repo":[{"repo":"huyvvo/rOSD","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"5cec8279a0db9459564b150572b515a6c08eaeb274116b3f2605bb9a904e65b7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}