{"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/benchmarking-and-analysis-of-unsupervised","title":"Benchmarking and Analysis of Unsupervised Object Segmentation from Real-world Single Images","arxiv_id":"2312.04947","date":"2023-12-08","proceeding":null,"authors":["Yafei Yang","Bo Yang"],"abstract":"In this paper, we study the problem of unsupervised object segmentation from single images. We do not introduce a new algorithm, but systematically investigate the effectiveness of existing unsupervised models on challenging real-world images. We first introduce seven complexity factors to quantitatively measure the distributions of background and foreground object biases in appearance and geometry for datasets with human annotations. With the aid of these factors, we empirically find that, not surprisingly, existing unsupervised models fail to segment generic objects in real-world images, although they can easily achieve excellent performance on numerous simple synthetic datasets, due to the vast gap in objectness biases between synthetic and real images. By conducting extensive experiments on multiple groups of ablated real-world datasets, we ultimately find that the key factors underlying the failure of existing unsupervised models on real-world images are the challenging distributions of background and foreground object biases in appearance and geometry. Because of this, the inductive biases introduced in existing unsupervised models can hardly capture the diverse object distributions. Our research results suggest that future work should exploit more explicit objectness biases in the network design.","url_abs":"https://arxiv.org/abs/2312.04947v1","url_pdf":"https://arxiv.org/pdf/2312.04947v1.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":"benchmarking-and-analysis-of-unsupervised","repo_url":"https://github.com/vlar-group/unsupobjseg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"object","task_name":"Object"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-object-segmentation","task_name":"Unsupervised Object Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.04947","atlas_url":"https://app.syntology.ai/?focus=2312.04947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04947"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vlar-group/unsupobjseg","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"2047d2acff2eedeb","entry":"dataset","repo":"vlar-group/unsupobjseg","repo_kind":"official","path":"IODINE/modules/dataloader.py","file_url":"https://github.com/vlar-group/unsupobjseg/blob/HEAD/IODINE/modules/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2047d2acff2eedeb"}},{"code_sha256_prefix":"54f836e2a8ca5c0a","entry":"spatial_broadcast","repo":"vlar-group/unsupobjseg","repo_kind":"official","path":"Slot_Attention/model.py","file_url":"https://github.com/vlar-group/unsupobjseg/blob/HEAD/Slot_Attention/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"54f836e2a8ca5c0a"}},{"code_sha256_prefix":"d0a5630e73c05e0d","entry":"spatial_flatten","repo":"vlar-group/unsupobjseg","repo_kind":"official","path":"Slot_Attention/model.py","file_url":"https://github.com/vlar-group/unsupobjseg/blob/HEAD/Slot_Attention/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d0a5630e73c05e0d"}},{"code_sha256_prefix":"7d4f8df3adcd3388","entry":"unstack_and_split","repo":"vlar-group/unsupobjseg","repo_kind":"official","path":"Slot_Attention/model.py","file_url":"https://github.com/vlar-group/unsupobjseg/blob/HEAD/Slot_Attention/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7d4f8df3adcd3388"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}