{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:PJGGM7ZXC3LNWDNPZ3JMEVBXWI","short_pith_number":"pith:PJGGM7ZX","schema_version":"1.0","canonical_sha256":"7a4c667f3716d6db0dafced2c25437b2263b6acd2584521f2c93ff9a949ea9f6","source":{"kind":"arxiv","id":"1406.2080","version":4},"attestation_state":"computed","paper":{"title":"Training Convolutional Networks with Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Joan Bruna, Lubomir Bourdev, Manohar Paluri, Rob Fergus, Sainbayar Sukhbaatar","submitted_at":"2014-06-09T05:45:12Z","abstract_excerpt":"The availability of large labeled datasets has allowed Convolutional Network models to achieve impressive recognition results. However, in many settings manual annotation of the data is impractical; instead our data has noisy labels, i.e. there is some freely available label for each image which may or may not be accurate. In this paper, we explore the performance of discriminatively-trained Convnets when trained on such noisy data. We introduce an extra noise layer into the network which adapts the network outputs to match the noisy label distribution. The parameters of this noise layer can b"},"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":"1406.2080","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-09T05:45:12Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"038452fdc1fe231fecb868a5a5026b5d8215af01c0448e14e85d576d95113bfe","abstract_canon_sha256":"fc66b4b17266147520139957353f7babbfcebbba60863a3319a27759c5b74a81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:08.440841Z","signature_b64":"vnMYL7ZLdB4YsdxPcg8sJciWEzBRnmwPzxya+xv1ge47UX/ofXgfITbUDfwdrVDcr7KVz3PbDgNSpKubZFZcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a4c667f3716d6db0dafced2c25437b2263b6acd2584521f2c93ff9a949ea9f6","last_reissued_at":"2026-05-18T02:19:08.440081Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:08.440081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Convolutional Networks with Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Joan Bruna, Lubomir Bourdev, Manohar Paluri, Rob Fergus, Sainbayar Sukhbaatar","submitted_at":"2014-06-09T05:45:12Z","abstract_excerpt":"The availability of large labeled datasets has allowed Convolutional Network models to achieve impressive recognition results. However, in many settings manual annotation of the data is impractical; instead our data has noisy labels, i.e. there is some freely available label for each image which may or may not be accurate. In this paper, we explore the performance of discriminatively-trained Convnets when trained on such noisy data. We introduce an extra noise layer into the network which adapts the network outputs to match the noisy label distribution. The parameters of this noise layer can b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.2080","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1406.2080","created_at":"2026-05-18T02:19:08.440209+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.2080v4","created_at":"2026-05-18T02:19:08.440209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.2080","created_at":"2026-05-18T02:19:08.440209+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJGGM7ZXC3LN","created_at":"2026-05-18T12:28:43.426989+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJGGM7ZXC3LNWDNP","created_at":"2026-05-18T12:28:43.426989+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJGGM7ZX","created_at":"2026-05-18T12:28:43.426989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1907.01742","citing_title":"Supervised Classifiers for Audio Impairments with Noisy Labels","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06167","citing_title":"FoodX-251: A Dataset for Fine-grained Food Classification","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11384","citing_title":"Product Image Recognition with Guidance Learning and Noisy Supervision","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2512.09315","citing_title":"Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlook","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08573","citing_title":"Silhouette Loss: Differentiable Global Structure Learning for Deep Representations","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03993","citing_title":"Can LLMs Learn to Reason Robustly under Noisy Supervision?","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJGGM7ZXC3LNWDNPZ3JMEVBXWI","json":"https://pith.science/pith/PJGGM7ZXC3LNWDNPZ3JMEVBXWI.json","graph_json":"https://pith.science/api/pith-number/PJGGM7ZXC3LNWDNPZ3JMEVBXWI/graph.json","events_json":"https://pith.science/api/pith-number/PJGGM7ZXC3LNWDNPZ3JMEVBXWI/events.json","paper":"https://pith.science/paper/PJGGM7ZX"},"agent_actions":{"view_html":"https://pith.science/pith/PJGGM7ZXC3LNWDNPZ3JMEVBXWI","download_json":"https://pith.science/pith/PJGGM7ZXC3LNWDNPZ3JMEVBXWI.json","view_paper":"https://pith.science/paper/PJGGM7ZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.2080&json=true","fetch_graph":"https://pith.science/api/pith-number/PJGGM7ZXC3LNWDNPZ3JMEVBXWI/graph.json","fetch_events":"https://pith.science/api/pith-number/PJGGM7ZXC3LNWDNPZ3JMEVBXWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJGGM7ZXC3LNWDNPZ3JMEVBXWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJGGM7ZXC3LNWDNPZ3JMEVBXWI/action/storage_attestation","attest_author":"https://pith.science/pith/PJGGM7ZXC3LNWDNPZ3JMEVBXWI/action/author_attestation","sign_citation":"https://pith.science/pith/PJGGM7ZXC3LNWDNPZ3JMEVBXWI/action/citation_signature","submit_replication":"https://pith.science/pith/PJGGM7ZXC3LNWDNPZ3JMEVBXWI/action/replication_record"}},"created_at":"2026-05-18T02:19:08.440209+00:00","updated_at":"2026-05-18T02:19:08.440209+00:00"}