{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3W25RMMEJ6X6CDVSRYV7ORDZVO","short_pith_number":"pith:3W25RMME","schema_version":"1.0","canonical_sha256":"ddb5d8b1844fafe10eb28e2bf74479ab99baffcc5a49fbb13f04e4db4d284590","source":{"kind":"arxiv","id":"2207.11518","version":2},"attestation_state":"computed","paper":{"title":"Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuanguang Yang, Fuzhen Zhuang, Helong Zhou, Qian Zhan, Yongjun Xu, Zhulin An","submitted_at":"2022-07-23T13:39:01Z","abstract_excerpt":"The teacher-free online Knowledge Distillation (KD) aims to train an ensemble of multiple student models collaboratively and distill knowledge from each other. Although existing online KD methods achieve desirable performance, they often focus on class probabilities as the core knowledge type, ignoring the valuable feature representational information. We present a Mutual Contrastive Learning (MCL) framework for online KD. The core idea of MCL is to perform mutual interaction and transfer of contrastive distributions among a cohort of networks in an online manner. Our MCL can aggregate cross-n"},"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":"2207.11518","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-23T13:39:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c7f47c3f665b95b5ede6dc2d67eabd5a3f65451f85bea404eb6a5a8c35cc5c6","abstract_canon_sha256":"83f3dc3fc7b61560fdc5da3b019ef58b05a3d761f86d0a84df66e943638e42ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:54.544345Z","signature_b64":"mSz746ZXHJ8t1PlH0Y6VLoXhcYAIdjKr4keuP/9Ik5R7tG98PYZBSV6y4AWcfdJbCLwOn2ZyqQ+HJbVCG2agBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddb5d8b1844fafe10eb28e2bf74479ab99baffcc5a49fbb13f04e4db4d284590","last_reissued_at":"2026-07-05T05:54:54.543872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:54.543872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuanguang Yang, Fuzhen Zhuang, Helong Zhou, Qian Zhan, Yongjun Xu, Zhulin An","submitted_at":"2022-07-23T13:39:01Z","abstract_excerpt":"The teacher-free online Knowledge Distillation (KD) aims to train an ensemble of multiple student models collaboratively and distill knowledge from each other. Although existing online KD methods achieve desirable performance, they often focus on class probabilities as the core knowledge type, ignoring the valuable feature representational information. We present a Mutual Contrastive Learning (MCL) framework for online KD. The core idea of MCL is to perform mutual interaction and transfer of contrastive distributions among a cohort of networks in an online manner. Our MCL can aggregate cross-n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.11518","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/2207.11518/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":"2207.11518","created_at":"2026-07-05T05:54:54.543931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.11518v2","created_at":"2026-07-05T05:54:54.543931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.11518","created_at":"2026-07-05T05:54:54.543931+00:00"},{"alias_kind":"pith_short_12","alias_value":"3W25RMMEJ6X6","created_at":"2026-07-05T05:54:54.543931+00:00"},{"alias_kind":"pith_short_16","alias_value":"3W25RMMEJ6X6CDVS","created_at":"2026-07-05T05:54:54.543931+00:00"},{"alias_kind":"pith_short_8","alias_value":"3W25RMME","created_at":"2026-07-05T05:54:54.543931+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/3W25RMMEJ6X6CDVSRYV7ORDZVO","json":"https://pith.science/pith/3W25RMMEJ6X6CDVSRYV7ORDZVO.json","graph_json":"https://pith.science/api/pith-number/3W25RMMEJ6X6CDVSRYV7ORDZVO/graph.json","events_json":"https://pith.science/api/pith-number/3W25RMMEJ6X6CDVSRYV7ORDZVO/events.json","paper":"https://pith.science/paper/3W25RMME"},"agent_actions":{"view_html":"https://pith.science/pith/3W25RMMEJ6X6CDVSRYV7ORDZVO","download_json":"https://pith.science/pith/3W25RMMEJ6X6CDVSRYV7ORDZVO.json","view_paper":"https://pith.science/paper/3W25RMME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.11518&json=true","fetch_graph":"https://pith.science/api/pith-number/3W25RMMEJ6X6CDVSRYV7ORDZVO/graph.json","fetch_events":"https://pith.science/api/pith-number/3W25RMMEJ6X6CDVSRYV7ORDZVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3W25RMMEJ6X6CDVSRYV7ORDZVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3W25RMMEJ6X6CDVSRYV7ORDZVO/action/storage_attestation","attest_author":"https://pith.science/pith/3W25RMMEJ6X6CDVSRYV7ORDZVO/action/author_attestation","sign_citation":"https://pith.science/pith/3W25RMMEJ6X6CDVSRYV7ORDZVO/action/citation_signature","submit_replication":"https://pith.science/pith/3W25RMMEJ6X6CDVSRYV7ORDZVO/action/replication_record"}},"created_at":"2026-07-05T05:54:54.543931+00:00","updated_at":"2026-07-05T05:54:54.543931+00:00"}