{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WG5NWJ6JWHHJ5RQ2LNFAGFYZU5","short_pith_number":"pith:WG5NWJ6J","schema_version":"1.0","canonical_sha256":"b1badb27c9b1ce9ec61a5b4a031719a74b291964bfa67ee611210ad4c376b4f1","source":{"kind":"arxiv","id":"2403.05894","version":1},"attestation_state":"computed","paper":{"title":"Frequency Attention for Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cuong Pham, Dinh Phung, Gustavo Carneiro, Thanh-Toan Do, Trung Le, Van-Anh Nguyen","submitted_at":"2024-03-09T12:18:48Z","abstract_excerpt":"Knowledge distillation is an attractive approach for learning compact deep neural networks, which learns a lightweight student model by distilling knowledge from a complex teacher model. Attention-based knowledge distillation is a specific form of intermediate feature-based knowledge distillation that uses attention mechanisms to encourage the student to better mimic the teacher. However, most of the previous attention-based distillation approaches perform attention in the spatial domain, which primarily affects local regions in the input image. This may not be sufficient when we need to captu"},"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":"2403.05894","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-09T12:18:48Z","cross_cats_sorted":[],"title_canon_sha256":"631f61a3294037627b88e70b28bd47bbd888aa3afdcb12a46297bf81782d9d9d","abstract_canon_sha256":"118c95a7723cbf2b0f921f70655f00f7980d30fcc318f2cc300d9f7a707eb05b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:15.274707Z","signature_b64":"CCEvdx6hXvnb3kJoPa5UplNNaFx2EdCxVUVg62TtXn3tZvtXFIDMj7pX8NGTZr82kBgMrGIo54o0bZTkSKNXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1badb27c9b1ce9ec61a5b4a031719a74b291964bfa67ee611210ad4c376b4f1","last_reissued_at":"2026-07-05T07:54:15.274244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:15.274244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frequency Attention for Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cuong Pham, Dinh Phung, Gustavo Carneiro, Thanh-Toan Do, Trung Le, Van-Anh Nguyen","submitted_at":"2024-03-09T12:18:48Z","abstract_excerpt":"Knowledge distillation is an attractive approach for learning compact deep neural networks, which learns a lightweight student model by distilling knowledge from a complex teacher model. Attention-based knowledge distillation is a specific form of intermediate feature-based knowledge distillation that uses attention mechanisms to encourage the student to better mimic the teacher. However, most of the previous attention-based distillation approaches perform attention in the spatial domain, which primarily affects local regions in the input image. This may not be sufficient when we need to captu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.05894","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/2403.05894/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":"2403.05894","created_at":"2026-07-05T07:54:15.274299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.05894v1","created_at":"2026-07-05T07:54:15.274299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.05894","created_at":"2026-07-05T07:54:15.274299+00:00"},{"alias_kind":"pith_short_12","alias_value":"WG5NWJ6JWHHJ","created_at":"2026-07-05T07:54:15.274299+00:00"},{"alias_kind":"pith_short_16","alias_value":"WG5NWJ6JWHHJ5RQ2","created_at":"2026-07-05T07:54:15.274299+00:00"},{"alias_kind":"pith_short_8","alias_value":"WG5NWJ6J","created_at":"2026-07-05T07:54:15.274299+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/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5","json":"https://pith.science/pith/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5.json","graph_json":"https://pith.science/api/pith-number/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5/graph.json","events_json":"https://pith.science/api/pith-number/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5/events.json","paper":"https://pith.science/paper/WG5NWJ6J"},"agent_actions":{"view_html":"https://pith.science/pith/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5","download_json":"https://pith.science/pith/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5.json","view_paper":"https://pith.science/paper/WG5NWJ6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.05894&json=true","fetch_graph":"https://pith.science/api/pith-number/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5/graph.json","fetch_events":"https://pith.science/api/pith-number/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5/action/storage_attestation","attest_author":"https://pith.science/pith/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5/action/author_attestation","sign_citation":"https://pith.science/pith/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5/action/citation_signature","submit_replication":"https://pith.science/pith/WG5NWJ6JWHHJ5RQ2LNFAGFYZU5/action/replication_record"}},"created_at":"2026-07-05T07:54:15.274299+00:00","updated_at":"2026-07-05T07:54:15.274299+00:00"}