{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YJH2QS4OAPSRFBCHUB3DZEEBZF","short_pith_number":"pith:YJH2QS4O","schema_version":"1.0","canonical_sha256":"c24fa84b8e03e5128447a0763c9081c96a0f535032de1ba506424dad956b8ad5","source":{"kind":"arxiv","id":"2105.10375","version":5},"attestation_state":"computed","paper":{"title":"An Efficient Training Approach for Very Large Scale Face Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baigui Sun, Hao Li, Kai Wang, Panpan Zhang, Shuo Wang, Xiaobo Wang, Xiaojiang Peng, Yang You, Zheng Zhu, Zhipeng Zhou","submitted_at":"2021-05-21T14:34:00Z","abstract_excerpt":"Face recognition has achieved significant progress in deep learning era due to the ultra-large-scale and welllabeled datasets. However, training on the outsize datasets is time-consuming and takes up a lot of hardware resource. Therefore, designing an efficient training approach is indispensable. The heavy computational and memory costs mainly result from the million-level dimensionality of thefully connected (FC) layer. To this end, we propose a novel training approach, termed Faster Face Classification (F2C), to alleviate time and cost without sacrificing the performance. This method adopts "},"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":"2105.10375","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-05-21T14:34:00Z","cross_cats_sorted":[],"title_canon_sha256":"3bc58bac56fc997aaada0997240c5fb3665bcb3232e2bbddfbf9ac05cb6e5635","abstract_canon_sha256":"76a2b60652b99c1cf04ba75c75a7f8fa71de9b6e75e0973dae3dbcb8cf46b63e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:41.669403Z","signature_b64":"sq8whaqaML5NK1DFkyPzejzp44ts4e6257WLzftHeDlNku5qzXZJ/ZAYAF+e1p+/fVmOL6D0d5pwgfM2ue+KCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c24fa84b8e03e5128447a0763c9081c96a0f535032de1ba506424dad956b8ad5","last_reissued_at":"2026-07-05T04:01:41.668910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:41.668910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Efficient Training Approach for Very Large Scale Face Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baigui Sun, Hao Li, Kai Wang, Panpan Zhang, Shuo Wang, Xiaobo Wang, Xiaojiang Peng, Yang You, Zheng Zhu, Zhipeng Zhou","submitted_at":"2021-05-21T14:34:00Z","abstract_excerpt":"Face recognition has achieved significant progress in deep learning era due to the ultra-large-scale and welllabeled datasets. However, training on the outsize datasets is time-consuming and takes up a lot of hardware resource. Therefore, designing an efficient training approach is indispensable. The heavy computational and memory costs mainly result from the million-level dimensionality of thefully connected (FC) layer. To this end, we propose a novel training approach, termed Faster Face Classification (F2C), to alleviate time and cost without sacrificing the performance. This method adopts "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.10375","kind":"arxiv","version":5},"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/2105.10375/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":"2105.10375","created_at":"2026-07-05T04:01:41.668967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.10375v5","created_at":"2026-07-05T04:01:41.668967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.10375","created_at":"2026-07-05T04:01:41.668967+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJH2QS4OAPSR","created_at":"2026-07-05T04:01:41.668967+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJH2QS4OAPSRFBCH","created_at":"2026-07-05T04:01:41.668967+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJH2QS4O","created_at":"2026-07-05T04:01:41.668967+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/YJH2QS4OAPSRFBCHUB3DZEEBZF","json":"https://pith.science/pith/YJH2QS4OAPSRFBCHUB3DZEEBZF.json","graph_json":"https://pith.science/api/pith-number/YJH2QS4OAPSRFBCHUB3DZEEBZF/graph.json","events_json":"https://pith.science/api/pith-number/YJH2QS4OAPSRFBCHUB3DZEEBZF/events.json","paper":"https://pith.science/paper/YJH2QS4O"},"agent_actions":{"view_html":"https://pith.science/pith/YJH2QS4OAPSRFBCHUB3DZEEBZF","download_json":"https://pith.science/pith/YJH2QS4OAPSRFBCHUB3DZEEBZF.json","view_paper":"https://pith.science/paper/YJH2QS4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.10375&json=true","fetch_graph":"https://pith.science/api/pith-number/YJH2QS4OAPSRFBCHUB3DZEEBZF/graph.json","fetch_events":"https://pith.science/api/pith-number/YJH2QS4OAPSRFBCHUB3DZEEBZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJH2QS4OAPSRFBCHUB3DZEEBZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJH2QS4OAPSRFBCHUB3DZEEBZF/action/storage_attestation","attest_author":"https://pith.science/pith/YJH2QS4OAPSRFBCHUB3DZEEBZF/action/author_attestation","sign_citation":"https://pith.science/pith/YJH2QS4OAPSRFBCHUB3DZEEBZF/action/citation_signature","submit_replication":"https://pith.science/pith/YJH2QS4OAPSRFBCHUB3DZEEBZF/action/replication_record"}},"created_at":"2026-07-05T04:01:41.668967+00:00","updated_at":"2026-07-05T04:01:41.668967+00:00"}