{"url":"/task/unsupervised-object-segmentation","name":"Unsupervised Object Segmentation","slug":"unsupervised-object-segmentation","description_markdown":"Image credit: [ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation](https://paperswithcode.com/paper/clevrtex-a-texture-rich-benchmark-for)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":39,"papers_with_code":23,"benchmarks":9,"benchmark_tables_in_archive":9,"benchmark_tables_shown":9,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":11,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/unsupervised-object-segmentation-on-clevrtex","slug":"unsupervised-object-segmentation-on-clevrtex","dataset":"ClevrTex","dataset_url":"/dataset/clevrtex","rows_in_archive":12,"metrics":["mIoU","MSE"],"first_row_in_archive_order":{"model":"AST-Seg-B3-CT","paper_title":"Unsupervised Multi-object Segmentation Using Attention and Soft-argmax","paper_url":"/paper/unsupervised-multi-object-segmentation-using","paper_date":"2022-05-26","arxiv_id":"2205.13271","code_links":[{"title":"BrunoSauvalle/AST","url":"https://github.com/BrunoSauvalle/AST"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-object-segmentation-on-davis","slug":"unsupervised-object-segmentation-on-davis","dataset":"DAVIS 2016","dataset_url":"/dataset/davis-2016","rows_in_archive":9,"metrics":["J score"],"first_row_in_archive_order":{"model":"RCF (with Post-Processing)","paper_title":"Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping","paper_url":"/paper/bootstrapping-objectness-from-videos-by","paper_date":"2023-04-17","arxiv_id":"2304.08025","code_links":[{"title":"TonyLianLong/RCF-UnsupVideoSeg","url":"https://github.com/TonyLianLong/RCF-UnsupVideoSeg"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-object-segmentation-on-segtrack","slug":"unsupervised-object-segmentation-on-segtrack","dataset":"SegTrack-v2","dataset_url":"/dataset/segtrack-v2-1","rows_in_archive":8,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"RCF (with post-processing)","paper_title":"Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping","paper_url":"/paper/bootstrapping-objectness-from-videos-by","paper_date":"2023-04-17","arxiv_id":"2304.08025","code_links":[{"title":"TonyLianLong/RCF-UnsupVideoSeg","url":"https://github.com/TonyLianLong/RCF-UnsupVideoSeg"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-object-segmentation-on-fbms-59","slug":"unsupervised-object-segmentation-on-fbms-59","dataset":"FBMS-59","dataset_url":"/dataset/fbms-59","rows_in_archive":7,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"RCF (with post-processing)","paper_title":"Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping","paper_url":"/paper/bootstrapping-objectness-from-videos-by","paper_date":"2023-04-17","arxiv_id":"2304.08025","code_links":[{"title":"TonyLianLong/RCF-UnsupVideoSeg","url":"https://github.com/TonyLianLong/RCF-UnsupVideoSeg"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-object-segmentation-on","slug":"unsupervised-object-segmentation-on","dataset":"ShapeStacks","dataset_url":"/dataset/shapestacks","rows_in_archive":5,"metrics":["ARI-FG"],"first_row_in_archive_order":{"model":"AST","paper_title":"Unsupervised Multi-object Segmentation Using Attention and Soft-argmax","paper_url":"/paper/unsupervised-multi-object-segmentation-using","paper_date":"2022-05-26","arxiv_id":"2205.13271","code_links":[{"title":"BrunoSauvalle/AST","url":"https://github.com/BrunoSauvalle/AST"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-object-segmentation-on-1","slug":"unsupervised-object-segmentation-on-1","dataset":"ObjectsRoom","dataset_url":"/dataset/objectsroom","rows_in_archive":5,"metrics":["ARI-FG"],"first_row_in_archive_order":{"model":"AST","paper_title":"Unsupervised Multi-object Segmentation Using Attention and Soft-argmax","paper_url":"/paper/unsupervised-multi-object-segmentation-using","paper_date":"2022-05-26","arxiv_id":"2205.13271","code_links":[{"title":"BrunoSauvalle/AST","url":"https://github.com/BrunoSauvalle/AST"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-object-segmentation-on-shelf","slug":"unsupervised-object-segmentation-on-shelf","dataset":"Shelf&Tote Training Dataset","dataset_url":"/dataset/shelf-tote-training-dataset","rows_in_archive":4,"metrics":["ARI"],"first_row_in_archive_order":{"model":"GENESIS-V2","paper_title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","paper_url":"/paper/genesis-v2-inferring-unordered-object","paper_date":"2021-04-20","arxiv_id":"2104.09958","code_links":[{"title":"applied-ai-lab/genesis","url":"https://github.com/applied-ai-lab/genesis"},{"title":"jinyangyuan/genesis","url":"https://github.com/jinyangyuan/genesis"}],"syntology":null}},{"leaderboard":"/sota/unsupervised-object-segmentation-on-ecssd","slug":"unsupervised-object-segmentation-on-ecssd","dataset":"ECSSD","dataset_url":"/dataset/ecssd","rows_in_archive":2,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"UnSegArmaNet","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/unsupervised-object-segmentation-on-duts","slug":"unsupervised-object-segmentation-on-duts","dataset":"DUTS","dataset_url":"/dataset/duts","rows_in_archive":1,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"DeepCut","paper_title":"DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering","paper_url":"/paper/deepcut-unsupervised-segmentation-using-graph","paper_date":"2022-12-12","arxiv_id":"2212.05853","code_links":[{"title":"sampl-weizmann/deepcut","url":"https://github.com/sampl-weizmann/deepcut"}],"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/duts","name":"DUTS","full_name":"","num_papers_in_archive":286},{"url":"/dataset/davis-2016","name":"DAVIS 2016","full_name":"DAVIS 2016","num_papers_in_archive":231},{"url":"/dataset/fbms","name":"FBMS","full_name":"Freiburg-Berkeley Motion Segmentation","num_papers_in_archive":126},{"url":"/dataset/segtrack-v2-1","name":"SegTrack-v2","full_name":"","num_papers_in_archive":107},{"url":"/dataset/ecssd","name":"ECSSD","full_name":"Extended Complex Scene Saliency Dataset","num_papers_in_archive":34},{"url":"/dataset/clevrtex","name":"ClevrTex","full_name":"","num_papers_in_archive":33},{"url":"/dataset/multi-dsprites","name":"Multi-dSprites","full_name":"","num_papers_in_archive":31},{"url":"/dataset/shapestacks","name":"ShapeStacks","full_name":"","num_papers_in_archive":22},{"url":"/dataset/fbms-59","name":"FBMS-59","full_name":"Freiburg-Berkeley Motion Segmentation","num_papers_in_archive":19},{"url":"/dataset/objectsroom","name":"ObjectsRoom","full_name":"","num_papers_in_archive":5},{"url":"/dataset/shelf-tote-training-dataset","name":"Shelf&Tote Training Dataset","full_name":"MIT-Princeton Amazon Picking Challenge 2016 Shelf&Tote Training Dataset","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/instance-segmentation","name":"Instance Segmentation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":23,"of":23,"tagged_in_all":39,"items":[{"url":"/paper/multi-object-representation-learning-with","title":"Multi-Object Representation Learning with Iterative Variational Inference","date":"2019-03-01","arxiv_id":"1903.00450","repositories_listed":6,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/monet-unsupervised-scene-decomposition-and","title":"MONet: Unsupervised Scene Decomposition and Representation","date":"2019-01-22","arxiv_id":"1901.11390","repositories_listed":5,"syntology":{"n":7,"n_ran":1,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/unsupervised-image-decomposition-with-phase","title":"Unsupervised Image Decomposition with Phase-Correlation Networks","date":"2021-10-07","arxiv_id":"2110.03473","repositories_listed":2,"syntology":null},{"url":"/paper/genesis-v2-inferring-unordered-object","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","date":"2021-04-20","arxiv_id":"2104.09958","repositories_listed":2,"syntology":null},{"url":"/paper/genesis-generative-scene-inference-and","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","date":"2019-07-30","arxiv_id":"1907.13052","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-detect-and-segment-mobile-objects","title":"MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos","date":"2024-05-23","arxiv_id":"2405.14841","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/benchmarking-and-analysis-of-unsupervised","title":"Benchmarking and Analysis of Unsupervised Object Segmentation from Real-world Single Images","date":"2023-12-08","arxiv_id":"2312.04947","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/spot-self-training-with-patch-order","title":"SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers","date":"2023-12-01","arxiv_id":"2312.00648","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/bootstrapping-objectness-from-videos-by","title":"Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping","date":"2023-04-17","arxiv_id":"2304.08025","repositories_listed":1,"syntology":null},{"url":"/paper/deepcut-unsupervised-segmentation-using-graph","title":"DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering","date":"2022-12-12","arxiv_id":"2212.05853","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/ilsgan-independent-layer-synthesis-for","title":"ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background Segmentation","date":"2022-11-25","arxiv_id":"2211.13974","repositories_listed":1,"syntology":null},{"url":"/paper/promising-or-elusive-unsupervised-object","title":"Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Images","date":"2022-10-05","arxiv_id":"2210.02324","repositories_listed":1,"syntology":null},{"url":"/paper/a-simple-and-powerful-global-optimization-for","title":"A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation","date":"2022-09-19","arxiv_id":"2209.09341","repositories_listed":1,"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/refine-and-represent-region-to-object","title":"Refine and Represent: Region-to-Object Representation Learning","date":"2022-08-25","arxiv_id":"2208.11821","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/segmenting-moving-objects-via-an-object","title":"Segmenting Moving Objects via an Object-Centric Layered Representation","date":"2022-07-05","arxiv_id":"2207.02206","repositories_listed":1,"syntology":{"n":21,"n_ran":16,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/unsupervised-multi-object-segmentation-using","title":"Unsupervised Multi-object Segmentation Using Attention and Soft-argmax","date":"2022-05-26","arxiv_id":"2205.13271","repositories_listed":1,"syntology":null},{"url":"/paper/em-driven-unsupervised-learning-for-efficient","title":"EM-driven unsupervised learning for efficient motion segmentation","date":"2022-01-06","arxiv_id":"2201.02074","repositories_listed":1,"syntology":null},{"url":"/paper/clevrtex-a-texture-rich-benchmark-for","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","date":"2021-11-19","arxiv_id":"2111.10265","repositories_listed":1,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/the-emergence-of-objectness-learning-zero","title":"The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos","date":"2021-11-11","arxiv_id":"2111.06394","repositories_listed":1,"syntology":null},{"url":"/paper/big-gans-are-watching-you-towards","title":"Object Segmentation Without Labels with Large-Scale Generative Models","date":"2020-06-08","arxiv_id":"2006.04988","repositories_listed":1,"syntology":null},{"url":"/paper/emergence-of-object-segmentation-in-perturbed","title":"Emergence of Object Segmentation in Perturbed Generative Models","date":"2019-05-29","arxiv_id":"1905.12663","repositories_listed":1,"syntology":null},{"url":"/paper/object-discovery-with-a-copy-pasting-gan","title":"Object Discovery with a Copy-Pasting GAN","date":"2019-05-27","arxiv_id":"1905.11369","repositories_listed":1,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/190513539","title":"Unsupervised Object Segmentation by Redrawing","date":"2019-05-27","arxiv_id":"1905.13539","repositories_listed":1,"syntology":null}],"syntology_records":11,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":1,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}