{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NNRF2KSCCH7OSHUOR6GHHWFQGF","short_pith_number":"pith:NNRF2KSC","schema_version":"1.0","canonical_sha256":"6b625d2a4211fee91e8e8f8c73d8b0316d5855f5921c5ec70bf892f32620326d","source":{"kind":"arxiv","id":"1905.00546","version":1},"attestation_state":"computed","paper":{"title":"Billion-scale semi-supervised learning for image classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dhruv Mahajan, Herv\\'e J\\'egou, I. Zeki Yalniz, Kan Chen, Manohar Paluri","submitted_at":"2019-05-02T02:08:18Z","abstract_excerpt":"This paper presents a study of semi-supervised learning with large convolutional networks. We propose a pipeline, based on a teacher/student paradigm, that leverages a large collection of unlabelled images (up to 1 billion). Our main goal is to improve the performance for a given target architecture, like ResNet-50 or ResNext. We provide an extensive analysis of the success factors of our approach, which leads us to formulate some recommendations to produce high-accuracy models for image classification with semi-supervised learning. As a result, our approach brings important gains to standard "},"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":"1905.00546","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-02T02:08:18Z","cross_cats_sorted":[],"title_canon_sha256":"45404ae1a71121b84c91068e5c30f732fe1867b0af74d42d2188ecae52bd4030","abstract_canon_sha256":"8091d63507dcdc115b3150e19d04d0ca65ca37726c17c0adb6278ec6634361af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:11.599484Z","signature_b64":"C21dKqJ3oKRF4mNtQ19HxJMUgHKZoUnCXU8AtrL0pGHy9I4xKBcSqveDEzwkNrFFR7AFVbQj1DfoLsA9+ec3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b625d2a4211fee91e8e8f8c73d8b0316d5855f5921c5ec70bf892f32620326d","last_reissued_at":"2026-05-17T23:47:11.599079Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:11.599079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Billion-scale semi-supervised learning for image classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dhruv Mahajan, Herv\\'e J\\'egou, I. Zeki Yalniz, Kan Chen, Manohar Paluri","submitted_at":"2019-05-02T02:08:18Z","abstract_excerpt":"This paper presents a study of semi-supervised learning with large convolutional networks. We propose a pipeline, based on a teacher/student paradigm, that leverages a large collection of unlabelled images (up to 1 billion). Our main goal is to improve the performance for a given target architecture, like ResNet-50 or ResNext. We provide an extensive analysis of the success factors of our approach, which leads us to formulate some recommendations to produce high-accuracy models for image classification with semi-supervised learning. As a result, our approach brings important gains to standard "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00546","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":""},"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":"1905.00546","created_at":"2026-05-17T23:47:11.599151+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.00546v1","created_at":"2026-05-17T23:47:11.599151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00546","created_at":"2026-05-17T23:47:11.599151+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNRF2KSCCH7O","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNRF2KSCCH7OSHUO","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNRF2KSC","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2104.14294","citing_title":"Emerging Properties in Self-Supervised Vision Transformers","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2602.17251","citing_title":"SCOPE: Structured Prototype-Guided Adaptation for EEG Foundation Models with Limited Labels","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2109.08238","citing_title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16588","citing_title":"Vision Transformers Need Registers","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10306","citing_title":"SatReg: Regression-based Neural Architecture Search for Lightweight Satellite Image Segmentation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2304.07193","citing_title":"DINOv2: Learning Robust Visual Features without Supervision","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NNRF2KSCCH7OSHUOR6GHHWFQGF","json":"https://pith.science/pith/NNRF2KSCCH7OSHUOR6GHHWFQGF.json","graph_json":"https://pith.science/api/pith-number/NNRF2KSCCH7OSHUOR6GHHWFQGF/graph.json","events_json":"https://pith.science/api/pith-number/NNRF2KSCCH7OSHUOR6GHHWFQGF/events.json","paper":"https://pith.science/paper/NNRF2KSC"},"agent_actions":{"view_html":"https://pith.science/pith/NNRF2KSCCH7OSHUOR6GHHWFQGF","download_json":"https://pith.science/pith/NNRF2KSCCH7OSHUOR6GHHWFQGF.json","view_paper":"https://pith.science/paper/NNRF2KSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.00546&json=true","fetch_graph":"https://pith.science/api/pith-number/NNRF2KSCCH7OSHUOR6GHHWFQGF/graph.json","fetch_events":"https://pith.science/api/pith-number/NNRF2KSCCH7OSHUOR6GHHWFQGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNRF2KSCCH7OSHUOR6GHHWFQGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNRF2KSCCH7OSHUOR6GHHWFQGF/action/storage_attestation","attest_author":"https://pith.science/pith/NNRF2KSCCH7OSHUOR6GHHWFQGF/action/author_attestation","sign_citation":"https://pith.science/pith/NNRF2KSCCH7OSHUOR6GHHWFQGF/action/citation_signature","submit_replication":"https://pith.science/pith/NNRF2KSCCH7OSHUOR6GHHWFQGF/action/replication_record"}},"created_at":"2026-05-17T23:47:11.599151+00:00","updated_at":"2026-05-17T23:47:11.599151+00:00"}