{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GZILXAHXT5MUNJKZZNRQWZFFEA","short_pith_number":"pith:GZILXAHX","schema_version":"1.0","canonical_sha256":"3650bb80f79f5946a559cb630b64a5200d9c3273a1e19d7299b8bac506d9d472","source":{"kind":"arxiv","id":"2107.11626","version":1},"attestation_state":"computed","paper":{"title":"Multi-Label Image Classification with Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dinh Phung, Ethan Zhao, Jianfei Cai, Son D.Dao","submitted_at":"2021-07-24T15:00:47Z","abstract_excerpt":"Recently, as an effective way of learning latent representations, contrastive learning has been increasingly popular and successful in various domains. The success of constrastive learning in single-label classifications motivates us to leverage this learning framework to enhance distinctiveness for better performance in multi-label image classification. In this paper, we show that a direct application of contrastive learning can hardly improve in multi-label cases. Accordingly, we propose a novel framework for multi-label classification with contrastive learning in a fully supervised setting,"},"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":"2107.11626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-24T15:00:47Z","cross_cats_sorted":[],"title_canon_sha256":"fec5b45d576115c2da954acc54b378187d7a4edaad46e87e4bebcf1564541959","abstract_canon_sha256":"a698285af50cfc6d74196793d35ba85b7c7a062833695cad04f102b151cfde88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:35.685835Z","signature_b64":"V8VMWptdxnIbY7BiEcNwXi7DjtVev3ha3YYon6j/rhiCAwA1NCzWruiZ5PcdJxefC7FlfhXhFUCEcH76MnnzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3650bb80f79f5946a559cb630b64a5200d9c3273a1e19d7299b8bac506d9d472","last_reissued_at":"2026-07-05T03:00:35.685413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:35.685413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Label Image Classification with Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dinh Phung, Ethan Zhao, Jianfei Cai, Son D.Dao","submitted_at":"2021-07-24T15:00:47Z","abstract_excerpt":"Recently, as an effective way of learning latent representations, contrastive learning has been increasingly popular and successful in various domains. The success of constrastive learning in single-label classifications motivates us to leverage this learning framework to enhance distinctiveness for better performance in multi-label image classification. In this paper, we show that a direct application of contrastive learning can hardly improve in multi-label cases. Accordingly, we propose a novel framework for multi-label classification with contrastive learning in a fully supervised setting,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.11626","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/2107.11626/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":"2107.11626","created_at":"2026-07-05T03:00:35.685477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.11626v1","created_at":"2026-07-05T03:00:35.685477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.11626","created_at":"2026-07-05T03:00:35.685477+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZILXAHXT5MU","created_at":"2026-07-05T03:00:35.685477+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZILXAHXT5MUNJKZ","created_at":"2026-07-05T03:00:35.685477+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZILXAHX","created_at":"2026-07-05T03:00:35.685477+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04413","citing_title":"Enhancing Text-Based Hierarchical Multilabel Classification for Mobile Applications via Contrastive Learning","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZILXAHXT5MUNJKZZNRQWZFFEA","json":"https://pith.science/pith/GZILXAHXT5MUNJKZZNRQWZFFEA.json","graph_json":"https://pith.science/api/pith-number/GZILXAHXT5MUNJKZZNRQWZFFEA/graph.json","events_json":"https://pith.science/api/pith-number/GZILXAHXT5MUNJKZZNRQWZFFEA/events.json","paper":"https://pith.science/paper/GZILXAHX"},"agent_actions":{"view_html":"https://pith.science/pith/GZILXAHXT5MUNJKZZNRQWZFFEA","download_json":"https://pith.science/pith/GZILXAHXT5MUNJKZZNRQWZFFEA.json","view_paper":"https://pith.science/paper/GZILXAHX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.11626&json=true","fetch_graph":"https://pith.science/api/pith-number/GZILXAHXT5MUNJKZZNRQWZFFEA/graph.json","fetch_events":"https://pith.science/api/pith-number/GZILXAHXT5MUNJKZZNRQWZFFEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZILXAHXT5MUNJKZZNRQWZFFEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZILXAHXT5MUNJKZZNRQWZFFEA/action/storage_attestation","attest_author":"https://pith.science/pith/GZILXAHXT5MUNJKZZNRQWZFFEA/action/author_attestation","sign_citation":"https://pith.science/pith/GZILXAHXT5MUNJKZZNRQWZFFEA/action/citation_signature","submit_replication":"https://pith.science/pith/GZILXAHXT5MUNJKZZNRQWZFFEA/action/replication_record"}},"created_at":"2026-07-05T03:00:35.685477+00:00","updated_at":"2026-07-05T03:00:35.685477+00:00"}