{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PZC6YIBNMNOJZIOIKVPZ6H6YUY","short_pith_number":"pith:PZC6YIBN","schema_version":"1.0","canonical_sha256":"7e45ec202d635c9ca1c8555f9f1fd8a63f01e89e3db1d5a741dd0f1446878a38","source":{"kind":"arxiv","id":"2002.10964","version":2},"attestation_state":"computed","paper":{"title":"Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jinwoo Shin, Minsu Cho, Sangwoo Mo","submitted_at":"2020-02-25T15:30:17Z","abstract_excerpt":"Generative adversarial networks (GANs) have shown outstanding performance on a wide range of problems in computer vision, graphics, and machine learning, but often require numerous training data and heavy computational resources. To tackle this issue, several methods introduce a transfer learning technique in GAN training. They, however, are either prone to overfitting or limited to learning small distribution shifts. In this paper, we show that simple fine-tuning of GANs with frozen lower layers of the discriminator performs surprisingly well. This simple baseline, FreezeD, significantly outp"},"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":"2002.10964","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-25T15:30:17Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"3dbd561bb8ee94a68fdeffd96043ae7f25aec990817e074332975f39f725912c","abstract_canon_sha256":"9c4ecbc6eff442c43137e7c3ab5a861e1703d7a14564c340324bbd1bdfef9a05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:28.884970Z","signature_b64":"yc9e8OUJamvmBaJzzrEBSjHEj0jyM2t+LyipTXP2yzgnd3vxg8yGqK6K0zf/mIcwGJqp5lux7/fBqqpGqZK3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e45ec202d635c9ca1c8555f9f1fd8a63f01e89e3db1d5a741dd0f1446878a38","last_reissued_at":"2026-07-05T00:44:28.884631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:28.884631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jinwoo Shin, Minsu Cho, Sangwoo Mo","submitted_at":"2020-02-25T15:30:17Z","abstract_excerpt":"Generative adversarial networks (GANs) have shown outstanding performance on a wide range of problems in computer vision, graphics, and machine learning, but often require numerous training data and heavy computational resources. To tackle this issue, several methods introduce a transfer learning technique in GAN training. They, however, are either prone to overfitting or limited to learning small distribution shifts. In this paper, we show that simple fine-tuning of GANs with frozen lower layers of the discriminator performs surprisingly well. This simple baseline, FreezeD, significantly outp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10964","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/2002.10964/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":"2002.10964","created_at":"2026-07-05T00:44:28.884688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.10964v2","created_at":"2026-07-05T00:44:28.884688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10964","created_at":"2026-07-05T00:44:28.884688+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZC6YIBNMNOJ","created_at":"2026-07-05T00:44:28.884688+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZC6YIBNMNOJZIOI","created_at":"2026-07-05T00:44:28.884688+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZC6YIBN","created_at":"2026-07-05T00:44:28.884688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.09706","citing_title":"Hybrid Quantum-Classical Generative Adversarial Networks with Transfer Learning","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23888","citing_title":"Geometry Preserving Loss Functions Promote Improved Adaptation of Blackbox Generative Model","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZC6YIBNMNOJZIOIKVPZ6H6YUY","json":"https://pith.science/pith/PZC6YIBNMNOJZIOIKVPZ6H6YUY.json","graph_json":"https://pith.science/api/pith-number/PZC6YIBNMNOJZIOIKVPZ6H6YUY/graph.json","events_json":"https://pith.science/api/pith-number/PZC6YIBNMNOJZIOIKVPZ6H6YUY/events.json","paper":"https://pith.science/paper/PZC6YIBN"},"agent_actions":{"view_html":"https://pith.science/pith/PZC6YIBNMNOJZIOIKVPZ6H6YUY","download_json":"https://pith.science/pith/PZC6YIBNMNOJZIOIKVPZ6H6YUY.json","view_paper":"https://pith.science/paper/PZC6YIBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.10964&json=true","fetch_graph":"https://pith.science/api/pith-number/PZC6YIBNMNOJZIOIKVPZ6H6YUY/graph.json","fetch_events":"https://pith.science/api/pith-number/PZC6YIBNMNOJZIOIKVPZ6H6YUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZC6YIBNMNOJZIOIKVPZ6H6YUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZC6YIBNMNOJZIOIKVPZ6H6YUY/action/storage_attestation","attest_author":"https://pith.science/pith/PZC6YIBNMNOJZIOIKVPZ6H6YUY/action/author_attestation","sign_citation":"https://pith.science/pith/PZC6YIBNMNOJZIOIKVPZ6H6YUY/action/citation_signature","submit_replication":"https://pith.science/pith/PZC6YIBNMNOJZIOIKVPZ6H6YUY/action/replication_record"}},"created_at":"2026-07-05T00:44:28.884688+00:00","updated_at":"2026-07-05T00:44:28.884688+00:00"}