{"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/a-spectral-approach-to-unsupervised-object","title":"A 3D Convolutional Approach to Spectral Object Segmentation in Space and Time","arxiv_id":"1907.02731","date":"2019-07-05","proceeding":null,"authors":["Elena Burceanu","Marius Leordeanu"],"abstract":"We formulate object segmentation in video as a graph partitioning problem in space and time, in which nodes are pixels and their relations form local neighborhoods. We claim that the strongest cluster in this pixel-level graph represents the salient object segmentation. We compute the main cluster using a novel and fast 3D filtering technique that finds the spectral clustering solution, namely the principal eigenvector of the graph's adjacency matrix, without building the matrix explicitly - which would be intractable. Our method is based on the power iteration for finding the principal eigenvector of a matrix, which we prove is equivalent to performing a specific set of 3D convolutions in the space-time feature volume. This allows us to avoid creating the matrix and have a fast parallel implementation on GPU. We show that our method is much faster than classical power iteration applied directly on the adjacency matrix. Different from other works, ours is dedicated to preserving object consistency in space and time at the level of pixels. For that, it requires powerful pixel-wise features at the frame level. This makes it perfectly suitable for incorporating the output of a backbone network or other methods and fast-improving over their solution without supervision. In experiments, we obtain consistent improvement, with the same set of hyper-parameters, over the top state of the art methods on DAVIS-2016 dataset, both in unsupervised and semi-supervised tasks. We also achieve top results on the well-known SegTrackv2 dataset.","url_abs":"https://arxiv.org/abs/1907.02731v5","url_pdf":"https://arxiv.org/pdf/1907.02731v5.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":"a-spectral-approach-to-unsupervised-object","repo_url":"https://github.com/bit-ml/sfseg","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"unsupervised-video-object-segmentation","task_name":"Unsupervised Video Object Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"graph-partitioning","task_name":"graph partitioning"}],"methods":[{"method_slug":"3d-convolution","method_name":"3D Convolution"},{"method_slug":"spectral-clustering","method_name":"Spectral Clustering"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-davis-2016","task":"Semi-Supervised Video Object Segmentation","dataset":"DAVIS 2016","model":"SFSeg over OnAVOS","rank_in_archive_order":78,"of":78,"metrics":{"Jaccard (Mean)":"86.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1907.02731","atlas_url":"https://app.syntology.ai/?focus=1907.02731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.02731"}},"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/bit-ml/sfseg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"b16a5ea902b7610f","entry":"filt2D","repo":"bit-ml/sfseg","repo_kind":"official","path":"sfseg.py","file_url":"https://github.com/bit-ml/sfseg/blob/HEAD/sfseg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b16a5ea902b7610f"}},{"code_sha256_prefix":"cacea28c3bf32ea1","entry":"filt3D","repo":"bit-ml/sfseg","repo_kind":"official","path":"sfseg.py","file_url":"https://github.com/bit-ml/sfseg/blob/HEAD/sfseg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cacea28c3bf32ea1"}},{"code_sha256_prefix":"c525f346c505b025","entry":"stab_num","repo":"bit-ml/sfseg","repo_kind":"official","path":"sfseg.py","file_url":"https://github.com/bit-ml/sfseg/blob/HEAD/sfseg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c525f346c505b025"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}