{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AVVBUXUXHVRYBYKPIAX4UZCNIO","short_pith_number":"pith:AVVBUXUX","schema_version":"1.0","canonical_sha256":"056a1a5e973d6380e14f402fca644d43ad91105a82f6f8519d71bd9e3c2447ef","source":{"kind":"arxiv","id":"2103.09382","version":3},"attestation_state":"computed","paper":{"title":"SPICE: Semantic Pseudo-labeling for Image Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuang Niu, Ge Wang, Hongming Shan","submitted_at":"2021-03-17T00:52:27Z","abstract_excerpt":"The similarity among samples and the discrepancy between clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from the inaccurate estimation of either feature similarity or semantic discrepancy. In this paper, we present a Semantic Pseudo-labeling-based Image ClustEring (SPICE) framework, which divides the clustering network into a feature model for measuring the instance-level similarity and a clustering head for identifying the cluster-level discrepancy. We design two semantics-aware pseudo-labeling algorithms, prototype pseudo-labeling, and r"},"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":"2103.09382","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-17T00:52:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"99a9f78038251944e9280c68f5721c6c4039c33e4f02ce3989c9b54d2b387f19","abstract_canon_sha256":"cc1f3aea0ac804f55e1b847de1368b584fc6bd00185f6fd4f9d050f43adad0b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:58.960061Z","signature_b64":"h+2rXKZfxyJjyiFfukJ1mG2LQa+7aZBpEZ4kaFhQgkQGMhrhorkoQouSphgVjlLBf5wNk8T47w66/NaYnbaTDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"056a1a5e973d6380e14f402fca644d43ad91105a82f6f8519d71bd9e3c2447ef","last_reissued_at":"2026-07-05T05:17:58.959647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:58.959647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPICE: Semantic Pseudo-labeling for Image Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuang Niu, Ge Wang, Hongming Shan","submitted_at":"2021-03-17T00:52:27Z","abstract_excerpt":"The similarity among samples and the discrepancy between clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from the inaccurate estimation of either feature similarity or semantic discrepancy. In this paper, we present a Semantic Pseudo-labeling-based Image ClustEring (SPICE) framework, which divides the clustering network into a feature model for measuring the instance-level similarity and a clustering head for identifying the cluster-level discrepancy. We design two semantics-aware pseudo-labeling algorithms, prototype pseudo-labeling, and r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09382","kind":"arxiv","version":3},"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/2103.09382/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":"2103.09382","created_at":"2026-07-05T05:17:58.959703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.09382v3","created_at":"2026-07-05T05:17:58.959703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09382","created_at":"2026-07-05T05:17:58.959703+00:00"},{"alias_kind":"pith_short_12","alias_value":"AVVBUXUXHVRY","created_at":"2026-07-05T05:17:58.959703+00:00"},{"alias_kind":"pith_short_16","alias_value":"AVVBUXUXHVRYBYKP","created_at":"2026-07-05T05:17:58.959703+00:00"},{"alias_kind":"pith_short_8","alias_value":"AVVBUXUX","created_at":"2026-07-05T05:17:58.959703+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21743","citing_title":"Cohort Organized Learning: Clustering Through Agreement","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AVVBUXUXHVRYBYKPIAX4UZCNIO","json":"https://pith.science/pith/AVVBUXUXHVRYBYKPIAX4UZCNIO.json","graph_json":"https://pith.science/api/pith-number/AVVBUXUXHVRYBYKPIAX4UZCNIO/graph.json","events_json":"https://pith.science/api/pith-number/AVVBUXUXHVRYBYKPIAX4UZCNIO/events.json","paper":"https://pith.science/paper/AVVBUXUX"},"agent_actions":{"view_html":"https://pith.science/pith/AVVBUXUXHVRYBYKPIAX4UZCNIO","download_json":"https://pith.science/pith/AVVBUXUXHVRYBYKPIAX4UZCNIO.json","view_paper":"https://pith.science/paper/AVVBUXUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.09382&json=true","fetch_graph":"https://pith.science/api/pith-number/AVVBUXUXHVRYBYKPIAX4UZCNIO/graph.json","fetch_events":"https://pith.science/api/pith-number/AVVBUXUXHVRYBYKPIAX4UZCNIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AVVBUXUXHVRYBYKPIAX4UZCNIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AVVBUXUXHVRYBYKPIAX4UZCNIO/action/storage_attestation","attest_author":"https://pith.science/pith/AVVBUXUXHVRYBYKPIAX4UZCNIO/action/author_attestation","sign_citation":"https://pith.science/pith/AVVBUXUXHVRYBYKPIAX4UZCNIO/action/citation_signature","submit_replication":"https://pith.science/pith/AVVBUXUXHVRYBYKPIAX4UZCNIO/action/replication_record"}},"created_at":"2026-07-05T05:17:58.959703+00:00","updated_at":"2026-07-05T05:17:58.959703+00:00"}