{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KCF5VNEZ3PHPR775MGXGMHU2PO","short_pith_number":"pith:KCF5VNEZ","schema_version":"1.0","canonical_sha256":"508bdab499dbcef8fffd61ae661e9a7bbad15c8853bc003b0d4f717e92e2bd11","source":{"kind":"arxiv","id":"2104.05382","version":2},"attestation_state":"computed","paper":{"title":"Dual Discriminator Adversarial Distillation for Data-free Model Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Zhao, Hui Yu, Huiyu Zhou, Junyu Dong, Xin Sun","submitted_at":"2021-04-12T12:01:45Z","abstract_excerpt":"Knowledge distillation has been widely used to produce portable and efficient neural networks which can be well applied on edge devices for computer vision tasks. However, almost all top-performing knowledge distillation methods need to access the original training data, which usually has a huge size and is often unavailable. To tackle this problem, we propose a novel data-free approach in this paper, named Dual Discriminator Adversarial Distillation (DDAD) to distill a neural network without any training data or meta-data. To be specific, we use a generator to create samples through dual disc"},"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":"2104.05382","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-12T12:01:45Z","cross_cats_sorted":[],"title_canon_sha256":"a2a278f17109e6f91162f59f90923cbe1e5be18b8e99c869ec3b5c84a5d599f5","abstract_canon_sha256":"92479d723d93acf133265c51116cf69cecf65ff38ceac81c51e41184ac5cf249"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:01.534311Z","signature_b64":"9XLZF9nqFyS9e8/6ramX+4WTvZkSikVPpk38GOGZv6rqmE7oaV0IEE+3ruI7d1ERhZxP2+l3A4ge2vWKdwwOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"508bdab499dbcef8fffd61ae661e9a7bbad15c8853bc003b0d4f717e92e2bd11","last_reissued_at":"2026-07-05T03:20:01.533739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:01.533739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Discriminator Adversarial Distillation for Data-free Model Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoran Zhao, Hui Yu, Huiyu Zhou, Junyu Dong, Xin Sun","submitted_at":"2021-04-12T12:01:45Z","abstract_excerpt":"Knowledge distillation has been widely used to produce portable and efficient neural networks which can be well applied on edge devices for computer vision tasks. However, almost all top-performing knowledge distillation methods need to access the original training data, which usually has a huge size and is often unavailable. To tackle this problem, we propose a novel data-free approach in this paper, named Dual Discriminator Adversarial Distillation (DDAD) to distill a neural network without any training data or meta-data. To be specific, we use a generator to create samples through dual disc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05382","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/2104.05382/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":"2104.05382","created_at":"2026-07-05T03:20:01.533799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.05382v2","created_at":"2026-07-05T03:20:01.533799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05382","created_at":"2026-07-05T03:20:01.533799+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCF5VNEZ3PHP","created_at":"2026-07-05T03:20:01.533799+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCF5VNEZ3PHPR775","created_at":"2026-07-05T03:20:01.533799+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCF5VNEZ","created_at":"2026-07-05T03:20:01.533799+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/KCF5VNEZ3PHPR775MGXGMHU2PO","json":"https://pith.science/pith/KCF5VNEZ3PHPR775MGXGMHU2PO.json","graph_json":"https://pith.science/api/pith-number/KCF5VNEZ3PHPR775MGXGMHU2PO/graph.json","events_json":"https://pith.science/api/pith-number/KCF5VNEZ3PHPR775MGXGMHU2PO/events.json","paper":"https://pith.science/paper/KCF5VNEZ"},"agent_actions":{"view_html":"https://pith.science/pith/KCF5VNEZ3PHPR775MGXGMHU2PO","download_json":"https://pith.science/pith/KCF5VNEZ3PHPR775MGXGMHU2PO.json","view_paper":"https://pith.science/paper/KCF5VNEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.05382&json=true","fetch_graph":"https://pith.science/api/pith-number/KCF5VNEZ3PHPR775MGXGMHU2PO/graph.json","fetch_events":"https://pith.science/api/pith-number/KCF5VNEZ3PHPR775MGXGMHU2PO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCF5VNEZ3PHPR775MGXGMHU2PO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCF5VNEZ3PHPR775MGXGMHU2PO/action/storage_attestation","attest_author":"https://pith.science/pith/KCF5VNEZ3PHPR775MGXGMHU2PO/action/author_attestation","sign_citation":"https://pith.science/pith/KCF5VNEZ3PHPR775MGXGMHU2PO/action/citation_signature","submit_replication":"https://pith.science/pith/KCF5VNEZ3PHPR775MGXGMHU2PO/action/replication_record"}},"created_at":"2026-07-05T03:20:01.533799+00:00","updated_at":"2026-07-05T03:20:01.533799+00:00"}