{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WH7WITSK4L6BZ6ZU5FXHDASDGC","short_pith_number":"pith:WH7WITSK","schema_version":"1.0","canonical_sha256":"b1ff644e4ae2fc1cfb34e96e71824330b5f851dfeb847a826c08f0451bce490e","source":{"kind":"arxiv","id":"2012.04462","version":2},"attestation_state":"computed","paper":{"title":"Multi-Objective Interpolation Training for Robustness to Label Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diego Ortego, Eric Arazo, Kevin McGuinness, Noel E. O'Connor, Paul Albert","submitted_at":"2020-12-08T15:01:54Z","abstract_excerpt":"Deep neural networks trained with standard cross-entropy loss memorize noisy labels, which degrades their performance. Most research to mitigate this memorization proposes new robust classification loss functions. Conversely, we propose a Multi-Objective Interpolation Training (MOIT) approach that jointly exploits contrastive learning and classification to mutually help each other and boost performance against label noise. We show that standard supervised contrastive learning degrades in the presence of label noise and propose an interpolation training strategy to mitigate this behavior. We fu"},"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":"2012.04462","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T15:01:54Z","cross_cats_sorted":[],"title_canon_sha256":"064d1f3b1ac29853dd8f61e1111e815a86f0a00807a84af0088b61e33ae49c7f","abstract_canon_sha256":"f77d96b6678a2b4373a2b90c8b8348accbce54495252804e32524bd06e2c2b4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:12.467758Z","signature_b64":"XxqvGtpYxeOkIZ+5IuFKmrN5S1BLyxjBxWuKOOeVQc8GSe5VorCARTG1Pj4dr0OZnXNjX6BDObxFUJkuS+pzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1ff644e4ae2fc1cfb34e96e71824330b5f851dfeb847a826c08f0451bce490e","last_reissued_at":"2026-07-05T02:24:12.467372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:12.467372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Objective Interpolation Training for Robustness to Label Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Diego Ortego, Eric Arazo, Kevin McGuinness, Noel E. O'Connor, Paul Albert","submitted_at":"2020-12-08T15:01:54Z","abstract_excerpt":"Deep neural networks trained with standard cross-entropy loss memorize noisy labels, which degrades their performance. Most research to mitigate this memorization proposes new robust classification loss functions. Conversely, we propose a Multi-Objective Interpolation Training (MOIT) approach that jointly exploits contrastive learning and classification to mutually help each other and boost performance against label noise. We show that standard supervised contrastive learning degrades in the presence of label noise and propose an interpolation training strategy to mitigate this behavior. We fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04462","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/2012.04462/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":"2012.04462","created_at":"2026-07-05T02:24:12.467428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.04462v2","created_at":"2026-07-05T02:24:12.467428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04462","created_at":"2026-07-05T02:24:12.467428+00:00"},{"alias_kind":"pith_short_12","alias_value":"WH7WITSK4L6B","created_at":"2026-07-05T02:24:12.467428+00:00"},{"alias_kind":"pith_short_16","alias_value":"WH7WITSK4L6BZ6ZU","created_at":"2026-07-05T02:24:12.467428+00:00"},{"alias_kind":"pith_short_8","alias_value":"WH7WITSK","created_at":"2026-07-05T02:24:12.467428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04029","citing_title":"Securing Contrastive mmWave-based Human Activity Recognition against Adversarial Label Flipping","ref_index":2020,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WH7WITSK4L6BZ6ZU5FXHDASDGC","json":"https://pith.science/pith/WH7WITSK4L6BZ6ZU5FXHDASDGC.json","graph_json":"https://pith.science/api/pith-number/WH7WITSK4L6BZ6ZU5FXHDASDGC/graph.json","events_json":"https://pith.science/api/pith-number/WH7WITSK4L6BZ6ZU5FXHDASDGC/events.json","paper":"https://pith.science/paper/WH7WITSK"},"agent_actions":{"view_html":"https://pith.science/pith/WH7WITSK4L6BZ6ZU5FXHDASDGC","download_json":"https://pith.science/pith/WH7WITSK4L6BZ6ZU5FXHDASDGC.json","view_paper":"https://pith.science/paper/WH7WITSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.04462&json=true","fetch_graph":"https://pith.science/api/pith-number/WH7WITSK4L6BZ6ZU5FXHDASDGC/graph.json","fetch_events":"https://pith.science/api/pith-number/WH7WITSK4L6BZ6ZU5FXHDASDGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WH7WITSK4L6BZ6ZU5FXHDASDGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WH7WITSK4L6BZ6ZU5FXHDASDGC/action/storage_attestation","attest_author":"https://pith.science/pith/WH7WITSK4L6BZ6ZU5FXHDASDGC/action/author_attestation","sign_citation":"https://pith.science/pith/WH7WITSK4L6BZ6ZU5FXHDASDGC/action/citation_signature","submit_replication":"https://pith.science/pith/WH7WITSK4L6BZ6ZU5FXHDASDGC/action/replication_record"}},"created_at":"2026-07-05T02:24:12.467428+00:00","updated_at":"2026-07-05T02:24:12.467428+00:00"}