{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PTJF4A2HILSN4OOG2YKRJWVGAD","short_pith_number":"pith:PTJF4A2H","schema_version":"1.0","canonical_sha256":"7cd25e034742e4de39c6d61514daa600fe3b7e9b15599f2f7d314fd3590e6cf1","source":{"kind":"arxiv","id":"2401.12535","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyunjung Shim, Seoungyoon Kang, Seungho Lee","submitted_at":"2024-01-23T07:24:16Z","abstract_excerpt":"This study demonstrates a cost-effective approach to semantic segmentation using self-supervised vision transformers (SSVT). By freezing the SSVT backbone and training a lightweight segmentation head, our approach effectively utilizes imperfect labels, thereby improving robustness to label imperfections. Empirical experiments show significant performance improvements over existing methods for various annotation types, including scribble, point-level, and image-level labels. The research highlights the effectiveness of self-supervised vision transformers in dealing with imperfect labels, provid"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.12535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-23T07:24:16Z","cross_cats_sorted":[],"title_canon_sha256":"e94519761dc5e31f244128d7ecb33c56a2c4f5c664b0e9b3d6cf8a1ad134f93e","abstract_canon_sha256":"d69ef6bec82488758c4c328e2c89bd4d26c8f3eae34810d504d1db2c4211705c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:32.057024Z","signature_b64":"UbC15bfgZ9CO4jfm+Jgbw8FaBSyQBRMahzkH5uWJf0QSFYWsq+NhHyw24+1mwpPIXx3NzPNCM3oq5r6VqTT/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cd25e034742e4de39c6d61514daa600fe3b7e9b15599f2f7d314fd3590e6cf1","last_reissued_at":"2026-07-05T07:36:32.056601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:32.056601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyunjung Shim, Seoungyoon Kang, Seungho Lee","submitted_at":"2024-01-23T07:24:16Z","abstract_excerpt":"This study demonstrates a cost-effective approach to semantic segmentation using self-supervised vision transformers (SSVT). By freezing the SSVT backbone and training a lightweight segmentation head, our approach effectively utilizes imperfect labels, thereby improving robustness to label imperfections. Empirical experiments show significant performance improvements over existing methods for various annotation types, including scribble, point-level, and image-level labels. The research highlights the effectiveness of self-supervised vision transformers in dealing with imperfect labels, provid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12535","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.12535/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.12535","created_at":"2026-07-05T07:36:32.056664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12535v1","created_at":"2026-07-05T07:36:32.056664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12535","created_at":"2026-07-05T07:36:32.056664+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTJF4A2HILSN","created_at":"2026-07-05T07:36:32.056664+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTJF4A2HILSN4OOG","created_at":"2026-07-05T07:36:32.056664+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTJF4A2H","created_at":"2026-07-05T07:36:32.056664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2603.01115","citing_title":"LUMOS: Latent Universal Medical Priors for Segmentation","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PTJF4A2HILSN4OOG2YKRJWVGAD","json":"https://pith.science/pith/PTJF4A2HILSN4OOG2YKRJWVGAD.json","graph_json":"https://pith.science/api/pith-number/PTJF4A2HILSN4OOG2YKRJWVGAD/graph.json","events_json":"https://pith.science/api/pith-number/PTJF4A2HILSN4OOG2YKRJWVGAD/events.json","paper":"https://pith.science/paper/PTJF4A2H"},"agent_actions":{"view_html":"https://pith.science/pith/PTJF4A2HILSN4OOG2YKRJWVGAD","download_json":"https://pith.science/pith/PTJF4A2HILSN4OOG2YKRJWVGAD.json","view_paper":"https://pith.science/paper/PTJF4A2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12535&json=true","fetch_graph":"https://pith.science/api/pith-number/PTJF4A2HILSN4OOG2YKRJWVGAD/graph.json","fetch_events":"https://pith.science/api/pith-number/PTJF4A2HILSN4OOG2YKRJWVGAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTJF4A2HILSN4OOG2YKRJWVGAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTJF4A2HILSN4OOG2YKRJWVGAD/action/storage_attestation","attest_author":"https://pith.science/pith/PTJF4A2HILSN4OOG2YKRJWVGAD/action/author_attestation","sign_citation":"https://pith.science/pith/PTJF4A2HILSN4OOG2YKRJWVGAD/action/citation_signature","submit_replication":"https://pith.science/pith/PTJF4A2HILSN4OOG2YKRJWVGAD/action/replication_record"}},"created_at":"2026-07-05T07:36:32.056664+00:00","updated_at":"2026-07-05T07:36:32.056664+00:00"}