{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BXWW7Y2WAT5XO2JMOCMFE5FNCR","short_pith_number":"pith:BXWW7Y2W","schema_version":"1.0","canonical_sha256":"0ded6fe35604fb77692c70985274ad146171dbbbca7f9e93a0b7b30ada7ecb53","source":{"kind":"arxiv","id":"1812.00660","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Distillation with Feature Maps for Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Che-Rung Lee, Chia-Che Chang, Chien-Yu Lu, Wei-Chun Chen","submitted_at":"2018-12-03T11:03:04Z","abstract_excerpt":"The model reduction problem that eases the computation costs and latency of complex deep learning architectures has received an increasing number of investigations owing to its importance in model deployment. One promising method is knowledge distillation (KD), which creates a fast-to-execute student model to mimic a large teacher network. In this paper, we propose a method, called KDFM (Knowledge Distillation with Feature Maps), which improves the effectiveness of KD by learning the feature maps from the teacher network. Two major techniques used in KDFM are shared classifier and generative a"},"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":"1812.00660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-03T11:03:04Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"6c0ab8d090663abf698de597ac00c75238b3533743f5668a1d3d91ea3aa4ec0a","abstract_canon_sha256":"27374e98671f1d4be9c4d31b64c02bbacd82dc6f27a4c62318693fd54e0d373a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:19.300123Z","signature_b64":"MXtU1n4eqyoQVcE1bEwAlrhuFgcWHH8UFQrw7Lv8X2XqWY5XmZHV4W5Kxer1ZWgingS/PqrA6pLti4vVy7ZsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ded6fe35604fb77692c70985274ad146171dbbbca7f9e93a0b7b30ada7ecb53","last_reissued_at":"2026-05-17T23:59:19.299792Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:19.299792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Distillation with Feature Maps for Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Che-Rung Lee, Chia-Che Chang, Chien-Yu Lu, Wei-Chun Chen","submitted_at":"2018-12-03T11:03:04Z","abstract_excerpt":"The model reduction problem that eases the computation costs and latency of complex deep learning architectures has received an increasing number of investigations owing to its importance in model deployment. One promising method is knowledge distillation (KD), which creates a fast-to-execute student model to mimic a large teacher network. In this paper, we propose a method, called KDFM (Knowledge Distillation with Feature Maps), which improves the effectiveness of KD by learning the feature maps from the teacher network. Two major techniques used in KDFM are shared classifier and generative a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00660","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":""},"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":"1812.00660","created_at":"2026-05-17T23:59:19.299839+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.00660v1","created_at":"2026-05-17T23:59:19.299839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00660","created_at":"2026-05-17T23:59:19.299839+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXWW7Y2WAT5X","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXWW7Y2WAT5XO2JM","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXWW7Y2W","created_at":"2026-05-18T12:32:16.446611+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/BXWW7Y2WAT5XO2JMOCMFE5FNCR","json":"https://pith.science/pith/BXWW7Y2WAT5XO2JMOCMFE5FNCR.json","graph_json":"https://pith.science/api/pith-number/BXWW7Y2WAT5XO2JMOCMFE5FNCR/graph.json","events_json":"https://pith.science/api/pith-number/BXWW7Y2WAT5XO2JMOCMFE5FNCR/events.json","paper":"https://pith.science/paper/BXWW7Y2W"},"agent_actions":{"view_html":"https://pith.science/pith/BXWW7Y2WAT5XO2JMOCMFE5FNCR","download_json":"https://pith.science/pith/BXWW7Y2WAT5XO2JMOCMFE5FNCR.json","view_paper":"https://pith.science/paper/BXWW7Y2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.00660&json=true","fetch_graph":"https://pith.science/api/pith-number/BXWW7Y2WAT5XO2JMOCMFE5FNCR/graph.json","fetch_events":"https://pith.science/api/pith-number/BXWW7Y2WAT5XO2JMOCMFE5FNCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXWW7Y2WAT5XO2JMOCMFE5FNCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXWW7Y2WAT5XO2JMOCMFE5FNCR/action/storage_attestation","attest_author":"https://pith.science/pith/BXWW7Y2WAT5XO2JMOCMFE5FNCR/action/author_attestation","sign_citation":"https://pith.science/pith/BXWW7Y2WAT5XO2JMOCMFE5FNCR/action/citation_signature","submit_replication":"https://pith.science/pith/BXWW7Y2WAT5XO2JMOCMFE5FNCR/action/replication_record"}},"created_at":"2026-05-17T23:59:19.299839+00:00","updated_at":"2026-05-17T23:59:19.299839+00:00"}