{"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/unsupervised-salient-object-detection-with","title":"Unsupervised Salient Object Detection with Spectral Cluster Voting","arxiv_id":"2203.12614","date":"2022-03-23","proceeding":null,"authors":["Gyungin Shin","Samuel Albanie","Weidi Xie"],"abstract":"In this paper, we tackle the challenging task of unsupervised salient object detection (SOD) by leveraging spectral clustering on self-supervised features. We make the following contributions: (i) We revisit spectral clustering and demonstrate its potential to group the pixels of salient objects; (ii) Given mask proposals from multiple applications of spectral clustering on image features computed from various self-supervised models, e.g., MoCov2, SwAV, DINO, we propose a simple but effective winner-takes-all voting mechanism for selecting the salient masks, leveraging object priors based on framing and distinctiveness; (iii) Using the selected object segmentation as pseudo groundtruth masks, we train a salient object detector, dubbed SelfMask, which outperforms prior approaches on three unsupervised SOD benchmarks. Code is publicly available at https://github.com/NoelShin/selfmask.","url_abs":"https://arxiv.org/abs/2203.12614v1","url_pdf":"https://arxiv.org/pdf/2203.12614v1.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":"unsupervised-salient-object-detection-with","repo_url":"https://github.com/noelshin/selfmask","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"salient-object-detection-1","task_name":"Salient Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-saliency-detection","task_name":"Unsupervised Saliency Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"lars","method_name":"LARS"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spectral-clustering","method_name":"Spectral Clustering"},{"method_slug":"swav","method_name":"SwAV"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-saliency-detection-on-dut-omron","task":"Unsupervised Saliency Detection","dataset":"DUT-OMRON","model":"SelfMask","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"91.9","IoU":"65.5","maximal F-measure":"85.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-saliency-detection-on-duts","task":"Unsupervised Saliency Detection","dataset":"DUTS","model":"SelfMask","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"93.3","IoU":"66","maximal F-measure":"88.2"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-saliency-detection-on-ecssd","task":"Unsupervised Saliency Detection","dataset":"ECSSD","model":"SelfMask","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"95.5","IoU":"81.8","maximal F-measure":"95.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.12614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.12614"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/noelshin/selfmask","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_fixture":2,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"noelshin/selfmask","repo_kind":"official","path":"networks/resnet_models.py","file_url":"https://github.com/noelshin/selfmask/blob/HEAD/networks/resnet_models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"55120f2026b56aa2","entry":"drop_path","repo":"noelshin/selfmask","repo_kind":"official","path":"networks/vision_transformer.py","file_url":"https://github.com/noelshin/selfmask/blob/HEAD/networks/vision_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"code_sha256_prefix":"915b71e73a54fc97","entry":"trunc_normal_","repo":"noelshin/selfmask","repo_kind":"official","path":"networks/vision_transformer.py","file_url":"https://github.com/noelshin/selfmask/blob/HEAD/networks/vision_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"915b71e73a54fc97"}},{"code_sha256_prefix":"66e194b18f29f1f2","entry":"ResNetBackbone","repo":"noelshin/selfmask","repo_kind":"official","path":"networks/resnet_backbone.py","file_url":"https://github.com/noelshin/selfmask/blob/HEAD/networks/resnet_backbone.py","link_basis":"harvester_set","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":"66e194b18f29f1f2"}},{"code_sha256_prefix":"5dac11fdc41c896b","entry":"checkpoint_filter_fn","repo":"noelshin/selfmask","repo_kind":"official","path":"networks/timm_vit.py","file_url":"https://github.com/noelshin/selfmask/blob/HEAD/networks/timm_vit.py","link_basis":"harvester_set","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":"5dac11fdc41c896b"}},{"code_sha256_prefix":"01b5be2b9eb52e62","entry":"deepbase_resnet18","repo":"noelshin/selfmask","repo_kind":"official","path":"networks/resnet_models.py","file_url":"https://github.com/noelshin/selfmask/blob/HEAD/networks/resnet_models.py","link_basis":"harvester_set","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":"01b5be2b9eb52e62"}},{"code_sha256_prefix":"dded96f53fb5aeb2","entry":"deit_tiny","repo":"noelshin/selfmask","repo_kind":"official","path":"networks/vision_transformer.py","file_url":"https://github.com/noelshin/selfmask/blob/HEAD/networks/vision_transformer.py","link_basis":"harvester_set","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":"dded96f53fb5aeb2"}},{"code_sha256_prefix":"1dbef2d4da4ee10f","entry":"resize_pos_embed","repo":"noelshin/selfmask","repo_kind":"official","path":"networks/timm_vit.py","file_url":"https://github.com/noelshin/selfmask/blob/HEAD/networks/timm_vit.py","link_basis":"harvester_set","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":"1dbef2d4da4ee10f"}},{"code_sha256_prefix":"11a05b824892ef2d","entry":"resnet18","repo":"noelshin/selfmask","repo_kind":"official","path":"networks/resnet_models.py","file_url":"https://github.com/noelshin/selfmask/blob/HEAD/networks/resnet_models.py","link_basis":"harvester_set","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":"11a05b824892ef2d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}