{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SJMXLIAA2OAWSD4BFYUAPKER7S","short_pith_number":"pith:SJMXLIAA","schema_version":"1.0","canonical_sha256":"925975a000d381690f812e2807a891fcb2d41e56b44d4e1ad4e44a4419d08a08","source":{"kind":"arxiv","id":"2205.13282","version":1},"attestation_state":"computed","paper":{"title":"On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Nicu Sebe, Wei Wang, Yue Song","submitted_at":"2022-05-26T11:41:36Z","abstract_excerpt":"The Fine-Grained Visual Categorization (FGVC) is challenging because the subtle inter-class variations are difficult to be captured. One notable research line uses the Global Covariance Pooling (GCP) layer to learn powerful representations with second-order statistics, which can effectively model inter-class differences. In our previous conference paper, we show that truncating small eigenvalues of the GCP covariance can attain smoother gradient and improve the performance on large-scale benchmarks. However, on fine-grained datasets, truncating the small eigenvalues would make the model fail t"},"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":"2205.13282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-26T11:41:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e47938df91de8a0e0fcf4f85804e00a09a4f0fdd97b902e3ba5b3552c88b6008","abstract_canon_sha256":"b021fa2968c34de29db0bca3b8e3b48c041de18c6645aefc102cad37fc3e7941"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:35.874402Z","signature_b64":"VYuk63w6a4NDVFOZR3+LOtwEyRM2A1gYYCAVppul31P0mOV1riAJrfUHXvTzn7w3rJL+/cYPntUWGx+hrH4gDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"925975a000d381690f812e2807a891fcb2d41e56b44d4e1ad4e44a4419d08a08","last_reissued_at":"2026-07-05T04:38:35.873901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:35.873901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Nicu Sebe, Wei Wang, Yue Song","submitted_at":"2022-05-26T11:41:36Z","abstract_excerpt":"The Fine-Grained Visual Categorization (FGVC) is challenging because the subtle inter-class variations are difficult to be captured. One notable research line uses the Global Covariance Pooling (GCP) layer to learn powerful representations with second-order statistics, which can effectively model inter-class differences. In our previous conference paper, we show that truncating small eigenvalues of the GCP covariance can attain smoother gradient and improve the performance on large-scale benchmarks. However, on fine-grained datasets, truncating the small eigenvalues would make the model fail t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.13282","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.13282/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":"2205.13282","created_at":"2026-07-05T04:38:35.873965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.13282v1","created_at":"2026-07-05T04:38:35.873965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.13282","created_at":"2026-07-05T04:38:35.873965+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJMXLIAA2OAW","created_at":"2026-07-05T04:38:35.873965+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJMXLIAA2OAWSD4B","created_at":"2026-07-05T04:38:35.873965+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJMXLIAA","created_at":"2026-07-05T04:38:35.873965+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/SJMXLIAA2OAWSD4BFYUAPKER7S","json":"https://pith.science/pith/SJMXLIAA2OAWSD4BFYUAPKER7S.json","graph_json":"https://pith.science/api/pith-number/SJMXLIAA2OAWSD4BFYUAPKER7S/graph.json","events_json":"https://pith.science/api/pith-number/SJMXLIAA2OAWSD4BFYUAPKER7S/events.json","paper":"https://pith.science/paper/SJMXLIAA"},"agent_actions":{"view_html":"https://pith.science/pith/SJMXLIAA2OAWSD4BFYUAPKER7S","download_json":"https://pith.science/pith/SJMXLIAA2OAWSD4BFYUAPKER7S.json","view_paper":"https://pith.science/paper/SJMXLIAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.13282&json=true","fetch_graph":"https://pith.science/api/pith-number/SJMXLIAA2OAWSD4BFYUAPKER7S/graph.json","fetch_events":"https://pith.science/api/pith-number/SJMXLIAA2OAWSD4BFYUAPKER7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJMXLIAA2OAWSD4BFYUAPKER7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJMXLIAA2OAWSD4BFYUAPKER7S/action/storage_attestation","attest_author":"https://pith.science/pith/SJMXLIAA2OAWSD4BFYUAPKER7S/action/author_attestation","sign_citation":"https://pith.science/pith/SJMXLIAA2OAWSD4BFYUAPKER7S/action/citation_signature","submit_replication":"https://pith.science/pith/SJMXLIAA2OAWSD4BFYUAPKER7S/action/replication_record"}},"created_at":"2026-07-05T04:38:35.873965+00:00","updated_at":"2026-07-05T04:38:35.873965+00:00"}