{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:VSF7YWHD5HONIDRHAW3LM2H523","short_pith_number":"pith:VSF7YWHD","schema_version":"1.0","canonical_sha256":"ac8bfc58e3e9dcd40e2705b6b668fdd6f7a93707c29b27c6874ac95d5d0f567e","source":{"kind":"arxiv","id":"1511.04534","version":2},"attestation_state":"computed","paper":{"title":"Learning Fine-grained Features via a CNN Tree for Large-scale Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Wang, Xingxing Wang, Zhenhua Wang","submitted_at":"2015-11-14T09:19:44Z","abstract_excerpt":"We propose a novel approach to enhance the discriminability of Convolutional Neural Networks (CNN). The key idea is to build a tree structure that could progressively learn fine-grained features to distinguish a subset of classes, by learning features only among these classes. Such features are expected to be more discriminative, compared to features learned for all the classes. We develop a new algorithm to effectively learn the tree structure from a large number of classes. Experiments on large-scale image classification tasks demonstrate that our method could boost the performance of a give"},"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":"1511.04534","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2015-11-14T09:19:44Z","cross_cats_sorted":[],"title_canon_sha256":"cf345185356dae990498072a1f51c38b044767ec0d77e4d15edb4dc6955dbad8","abstract_canon_sha256":"3bb0d7e509363c22056e746302c848ebf1c40be5e651087672f59ff513acfaa1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:35.508786Z","signature_b64":"8TIIZ7NLvhiEWPnAQaiyP64GYVzxThArODZj2nASa8PFAKCfRDovcIbPkn59OjFZGDOXsmODhM10VJuyZTmqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac8bfc58e3e9dcd40e2705b6b668fdd6f7a93707c29b27c6874ac95d5d0f567e","last_reissued_at":"2026-05-18T00:34:35.508391Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:35.508391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Fine-grained Features via a CNN Tree for Large-scale Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Wang, Xingxing Wang, Zhenhua Wang","submitted_at":"2015-11-14T09:19:44Z","abstract_excerpt":"We propose a novel approach to enhance the discriminability of Convolutional Neural Networks (CNN). The key idea is to build a tree structure that could progressively learn fine-grained features to distinguish a subset of classes, by learning features only among these classes. Such features are expected to be more discriminative, compared to features learned for all the classes. We develop a new algorithm to effectively learn the tree structure from a large number of classes. Experiments on large-scale image classification tasks demonstrate that our method could boost the performance of a give"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.04534","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":""},"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":"1511.04534","created_at":"2026-05-18T00:34:35.508458+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.04534v2","created_at":"2026-05-18T00:34:35.508458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.04534","created_at":"2026-05-18T00:34:35.508458+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSF7YWHD5HON","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSF7YWHD5HONIDRH","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSF7YWHD","created_at":"2026-05-18T12:29:47.479230+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/VSF7YWHD5HONIDRHAW3LM2H523","json":"https://pith.science/pith/VSF7YWHD5HONIDRHAW3LM2H523.json","graph_json":"https://pith.science/api/pith-number/VSF7YWHD5HONIDRHAW3LM2H523/graph.json","events_json":"https://pith.science/api/pith-number/VSF7YWHD5HONIDRHAW3LM2H523/events.json","paper":"https://pith.science/paper/VSF7YWHD"},"agent_actions":{"view_html":"https://pith.science/pith/VSF7YWHD5HONIDRHAW3LM2H523","download_json":"https://pith.science/pith/VSF7YWHD5HONIDRHAW3LM2H523.json","view_paper":"https://pith.science/paper/VSF7YWHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.04534&json=true","fetch_graph":"https://pith.science/api/pith-number/VSF7YWHD5HONIDRHAW3LM2H523/graph.json","fetch_events":"https://pith.science/api/pith-number/VSF7YWHD5HONIDRHAW3LM2H523/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSF7YWHD5HONIDRHAW3LM2H523/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSF7YWHD5HONIDRHAW3LM2H523/action/storage_attestation","attest_author":"https://pith.science/pith/VSF7YWHD5HONIDRHAW3LM2H523/action/author_attestation","sign_citation":"https://pith.science/pith/VSF7YWHD5HONIDRHAW3LM2H523/action/citation_signature","submit_replication":"https://pith.science/pith/VSF7YWHD5HONIDRHAW3LM2H523/action/replication_record"}},"created_at":"2026-05-18T00:34:35.508458+00:00","updated_at":"2026-05-18T00:34:35.508458+00:00"}