{"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/betrayed-by-attention-a-simple-yet-effective","title":"Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation","arxiv_id":"2311.17893","date":"2023-11-29","proceeding":null,"authors":["Shuangrui Ding","Rui Qian","Haohang Xu","Dahua Lin","Hongkai Xiong"],"abstract":"In this paper, we propose a simple yet effective approach for self-supervised video object segmentation (VOS). Our key insight is that the inherent structural dependencies present in DINO-pretrained Transformers can be leveraged to establish robust spatio-temporal correspondences in videos. Furthermore, simple clustering on this correspondence cue is sufficient to yield competitive segmentation results. Previous self-supervised VOS techniques majorly resort to auxiliary modalities or utilize iterative slot attention to assist in object discovery, which restricts their general applicability and imposes higher computational requirements. To deal with these challenges, we develop a simplified architecture that capitalizes on the emerging objectness from DINO-pretrained Transformers, bypassing the need for additional modalities or slot attention. Specifically, we first introduce a single spatio-temporal Transformer block to process the frame-wise DINO features and establish spatio-temporal dependencies in the form of self-attention. Subsequently, utilizing these attention maps, we implement hierarchical clustering to generate object segmentation masks. To train the spatio-temporal block in a fully self-supervised manner, we employ semantic and dynamic motion consistency coupled with entropy normalization. Our method demonstrates state-of-the-art performance across multiple unsupervised VOS benchmarks and particularly excels in complex real-world multi-object video segmentation tasks such as DAVIS-17-Unsupervised and YouTube-VIS-19. The code and model checkpoints will be released at https://github.com/shvdiwnkozbw/SSL-UVOS.","url_abs":"https://arxiv.org/abs/2311.17893v2","url_pdf":"https://arxiv.org/pdf/2311.17893v2.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":"betrayed-by-attention-a-simple-yet-effective","repo_url":"https://github.com/shvdiwnkozbw/ssl-uvos","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-discovery","task_name":"Object Discovery"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dino","method_name":"DINO"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"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":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vos","method_name":"VOS"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.17893","atlas_url":"https://app.syntology.ai/?focus=2311.17893","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17893"}},"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/shvdiwnkozbw/ssl-uvos","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran":8,"unverified":2},"by_repo_kind":{"official":{"samples":12,"ran":10,"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":12,"samples":[{"code_sha256_prefix":"55120f2026b56aa2","entry":"drop_path","repo":"shvdiwnkozbw/ssl-uvos","repo_kind":"official","path":"src/model/vision_transformer.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/model/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"55120f2026b56aa2"}},{"code_sha256_prefix":"fb2519bb639a667c","entry":"get_frame_aug","repo":"shvdiwnkozbw/ssl-uvos","repo_kind":"official","path":"src/augment.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/augment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb2519bb639a667c"}},{"code_sha256_prefix":"a33c8b9d77fca6c7","entry":"hierarchical_cluster","repo":"shvdiwnkozbw/ssl-uvos","repo_kind":"official","path":"src/eval_oneshot.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/eval_oneshot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a33c8b9d77fca6c7"}},{"code_sha256_prefix":"e72a538ee0eee47d","entry":"kl_distance","repo":"shvdiwnkozbw/ssl-uvos","repo_kind":"official","path":"src/eval_oneshot.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/eval_oneshot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e72a538ee0eee47d"}},{"code_sha256_prefix":"e8f1b9aad850632e","entry":"mem_efficient_hierarchical_cluster","repo":"shvdiwnkozbw/ssl-uvos","repo_kind":"official","path":"src/eval_oneshot.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/eval_oneshot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e8f1b9aad850632e"}},{"code_sha256_prefix":"14b1cc74dcb694bf","entry":"n_patches","repo":"shvdiwnkozbw/ssl-uvos","repo_kind":"official","path":"src/augment.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/augment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"14b1cc74dcb694bf"}},{"code_sha256_prefix":"600497c0fb4eb8c7","entry":"patch_grid","repo":"shvdiwnkozbw/ssl-uvos","repo_kind":"official","path":"src/augment.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/augment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"600497c0fb4eb8c7"}},{"code_sha256_prefix":"1a881611262d51ef","entry":"readRGB","repo":"shvdiwnkozbw/ssl-uvos","repo_kind":"official","path":"src/data.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1a881611262d51ef"}},{"code_sha256_prefix":"a3d6633188714161","entry":"readSeg","repo":"shvdiwnkozbw/ssl-uvos","repo_kind":"official","path":"src/data.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a3d6633188714161"}},{"code_sha256_prefix":"915b71e73a54fc97","entry":"trunc_normal_","repo":"shvdiwnkozbw/ssl-uvos","repo_kind":"official","path":"src/model/vision_transformer.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/model/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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"915b71e73a54fc97"}},{"code_sha256_prefix":"66e3a4ecd2f2c205","entry":"Augment_GPU_pre","repo":"shvdiwnkozbw/ssl-uvos","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"66e3a4ecd2f2c205"}},{"code_sha256_prefix":"faaced6c07e0019e","entry":"vit_tiny","repo":"shvdiwnkozbw/ssl-uvos","repo_kind":"official","path":"src/model/vision_transformer.py","file_url":"https://github.com/shvdiwnkozbw/ssl-uvos/blob/HEAD/src/model/vision_transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"faaced6c07e0019e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}