{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TVET26FFJH3TT2PD3WYR23ZLVK","short_pith_number":"pith:TVET26FF","schema_version":"1.0","canonical_sha256":"9d493d78a549f739e9e3ddb11d6f2baaa04df88f77344e5a8a6b8ddcc711587b","source":{"kind":"arxiv","id":"2404.16348","version":2},"attestation_state":"computed","paper":{"title":"Dual Expert Distillation Network for Generalized Zero-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haozhao Wang, Jie Zhang, Jingcai Guo, Jingming Liang, Kang Wei, Xiaocheng Lu, Xiaofeng Cao, Zhijie Rao","submitted_at":"2024-04-25T05:59:42Z","abstract_excerpt":"Zero-shot learning has consistently yielded remarkable progress via modeling nuanced one-to-one visual-attribute correlation. Existing studies resort to refining a uniform mapping function to align and correlate the sample regions and subattributes, ignoring two crucial issues: 1) the inherent asymmetry of attributes; and 2) the unutilized channel information. This paper addresses these issues by introducing a simple yet effective approach, dubbed Dual Expert Distillation Network (DEDN), where two experts are dedicated to coarse- and fine-grained visual-attribute modeling, respectively. Concre"},"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":"2404.16348","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-25T05:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"4c0a54aff7247ec34e1229ace825ec5bf237fb581d62e634f144d63209dc3257","abstract_canon_sha256":"1d8cad7986d2245917992c15160edc14f9665d99cfb81de7f2fdda34e49286ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:14.096619Z","signature_b64":"DPw27zbBXys4TijFD32w2REJ0f3wrUTsagi3zLh2dcyiclgI19Hlx4ZfMsTEEfSnqPLGjE6TeVCAyFtuXytZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d493d78a549f739e9e3ddb11d6f2baaa04df88f77344e5a8a6b8ddcc711587b","last_reissued_at":"2026-07-05T08:13:14.096219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:14.096219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Expert Distillation Network for Generalized Zero-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haozhao Wang, Jie Zhang, Jingcai Guo, Jingming Liang, Kang Wei, Xiaocheng Lu, Xiaofeng Cao, Zhijie Rao","submitted_at":"2024-04-25T05:59:42Z","abstract_excerpt":"Zero-shot learning has consistently yielded remarkable progress via modeling nuanced one-to-one visual-attribute correlation. Existing studies resort to refining a uniform mapping function to align and correlate the sample regions and subattributes, ignoring two crucial issues: 1) the inherent asymmetry of attributes; and 2) the unutilized channel information. This paper addresses these issues by introducing a simple yet effective approach, dubbed Dual Expert Distillation Network (DEDN), where two experts are dedicated to coarse- and fine-grained visual-attribute modeling, respectively. Concre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16348","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.16348/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":"2404.16348","created_at":"2026-07-05T08:13:14.096275+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16348v2","created_at":"2026-07-05T08:13:14.096275+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16348","created_at":"2026-07-05T08:13:14.096275+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVET26FFJH3T","created_at":"2026-07-05T08:13:14.096275+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVET26FFJH3TT2PD","created_at":"2026-07-05T08:13:14.096275+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVET26FF","created_at":"2026-07-05T08:13:14.096275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19055","citing_title":"SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral Analysis","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVET26FFJH3TT2PD3WYR23ZLVK","json":"https://pith.science/pith/TVET26FFJH3TT2PD3WYR23ZLVK.json","graph_json":"https://pith.science/api/pith-number/TVET26FFJH3TT2PD3WYR23ZLVK/graph.json","events_json":"https://pith.science/api/pith-number/TVET26FFJH3TT2PD3WYR23ZLVK/events.json","paper":"https://pith.science/paper/TVET26FF"},"agent_actions":{"view_html":"https://pith.science/pith/TVET26FFJH3TT2PD3WYR23ZLVK","download_json":"https://pith.science/pith/TVET26FFJH3TT2PD3WYR23ZLVK.json","view_paper":"https://pith.science/paper/TVET26FF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16348&json=true","fetch_graph":"https://pith.science/api/pith-number/TVET26FFJH3TT2PD3WYR23ZLVK/graph.json","fetch_events":"https://pith.science/api/pith-number/TVET26FFJH3TT2PD3WYR23ZLVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVET26FFJH3TT2PD3WYR23ZLVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVET26FFJH3TT2PD3WYR23ZLVK/action/storage_attestation","attest_author":"https://pith.science/pith/TVET26FFJH3TT2PD3WYR23ZLVK/action/author_attestation","sign_citation":"https://pith.science/pith/TVET26FFJH3TT2PD3WYR23ZLVK/action/citation_signature","submit_replication":"https://pith.science/pith/TVET26FFJH3TT2PD3WYR23ZLVK/action/replication_record"}},"created_at":"2026-07-05T08:13:14.096275+00:00","updated_at":"2026-07-05T08:13:14.096275+00:00"}