{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Y4ID74G2ZM4YPDEXOI4OMPFY23","short_pith_number":"pith:Y4ID74G2","schema_version":"1.0","canonical_sha256":"c7103ff0dacb39878c977238e63cb8d6e042b2625ddf39a9b2499e4f639dc04c","source":{"kind":"arxiv","id":"2107.08712","version":2},"attestation_state":"computed","paper":{"title":"Exploring Set Similarity for Dense Self-supervised Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoxin Zhang, Mingming Gong, Nannan Wang, Pengfei Wan, Qiang Li, Tongliang Liu, Wen Zheng, Zhaoqing Wang","submitted_at":"2021-07-19T09:38:27Z","abstract_excerpt":"By considering the spatial correspondence, dense self-supervised representation learning has achieved superior performance on various dense prediction tasks. However, the pixel-level correspondence tends to be noisy because of many similar misleading pixels, e.g., backgrounds. To address this issue, in this paper, we propose to explore \\textbf{set} \\textbf{sim}ilarity (SetSim) for dense self-supervised representation learning. We generalize pixel-wise similarity learning to set-wise one to improve the robustness because sets contain more semantic and structure information. Specifically, by res"},"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":"2107.08712","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-19T09:38:27Z","cross_cats_sorted":[],"title_canon_sha256":"6da3a0ac6f9901b38f142afd24e6eb0acfef2f3112e275f438a014da65192ca7","abstract_canon_sha256":"d7bd589048bd6c5429ef59228c8996a657e3c5b10a2a7fa82f29a71f9e83892c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:03.615999Z","signature_b64":"EmlEWzKBlvSuHpPgrKnPSwNENJugDCL/RLqyGA9Nq3x5PoxUGSUDDDEh2IBsioii11fRlDfec7ccFH+tb1EfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7103ff0dacb39878c977238e63cb8d6e042b2625ddf39a9b2499e4f639dc04c","last_reissued_at":"2026-07-05T04:05:03.615522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:03.615522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Set Similarity for Dense Self-supervised Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoxin Zhang, Mingming Gong, Nannan Wang, Pengfei Wan, Qiang Li, Tongliang Liu, Wen Zheng, Zhaoqing Wang","submitted_at":"2021-07-19T09:38:27Z","abstract_excerpt":"By considering the spatial correspondence, dense self-supervised representation learning has achieved superior performance on various dense prediction tasks. However, the pixel-level correspondence tends to be noisy because of many similar misleading pixels, e.g., backgrounds. To address this issue, in this paper, we propose to explore \\textbf{set} \\textbf{sim}ilarity (SetSim) for dense self-supervised representation learning. We generalize pixel-wise similarity learning to set-wise one to improve the robustness because sets contain more semantic and structure information. Specifically, by res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08712","kind":"arxiv","version":2},"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/2107.08712/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":"2107.08712","created_at":"2026-07-05T04:05:03.615592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.08712v2","created_at":"2026-07-05T04:05:03.615592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08712","created_at":"2026-07-05T04:05:03.615592+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4ID74G2ZM4Y","created_at":"2026-07-05T04:05:03.615592+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4ID74G2ZM4YPDEX","created_at":"2026-07-05T04:05:03.615592+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4ID74G2","created_at":"2026-07-05T04:05:03.615592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y4ID74G2ZM4YPDEXOI4OMPFY23","json":"https://pith.science/pith/Y4ID74G2ZM4YPDEXOI4OMPFY23.json","graph_json":"https://pith.science/api/pith-number/Y4ID74G2ZM4YPDEXOI4OMPFY23/graph.json","events_json":"https://pith.science/api/pith-number/Y4ID74G2ZM4YPDEXOI4OMPFY23/events.json","paper":"https://pith.science/paper/Y4ID74G2"},"agent_actions":{"view_html":"https://pith.science/pith/Y4ID74G2ZM4YPDEXOI4OMPFY23","download_json":"https://pith.science/pith/Y4ID74G2ZM4YPDEXOI4OMPFY23.json","view_paper":"https://pith.science/paper/Y4ID74G2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.08712&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4ID74G2ZM4YPDEXOI4OMPFY23/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4ID74G2ZM4YPDEXOI4OMPFY23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4ID74G2ZM4YPDEXOI4OMPFY23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4ID74G2ZM4YPDEXOI4OMPFY23/action/storage_attestation","attest_author":"https://pith.science/pith/Y4ID74G2ZM4YPDEXOI4OMPFY23/action/author_attestation","sign_citation":"https://pith.science/pith/Y4ID74G2ZM4YPDEXOI4OMPFY23/action/citation_signature","submit_replication":"https://pith.science/pith/Y4ID74G2ZM4YPDEXOI4OMPFY23/action/replication_record"}},"created_at":"2026-07-05T04:05:03.615592+00:00","updated_at":"2026-07-05T04:05:03.615592+00:00"}