{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6KQSVLTX3Z4EBUDVECSMMQ7DHP","short_pith_number":"pith:6KQSVLTX","schema_version":"1.0","canonical_sha256":"f2a12aae77de7840d07520a4c643e33bea55c0a0852de6cf789bf96d9af5d621","source":{"kind":"arxiv","id":"2303.17158","version":1},"attestation_state":"computed","paper":{"title":"KD-DLGAN: Data Limited Image Generation via Knowledge Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Eric Xing, Fangneng Zhan, Kaiwen Cui, Shengcai Liao, Shijian Lu1, Yingchen Yu","submitted_at":"2023-03-30T05:36:06Z","abstract_excerpt":"Generative Adversarial Networks (GANs) rely heavily on large-scale training data for training high-quality image generation models. With limited training data, the GAN discriminator often suffers from severe overfitting which directly leads to degraded generation especially in generation diversity. Inspired by the recent advances in knowledge distillation (KD), we propose KD-DLGAN, a knowledge-distillation based generation framework that introduces pre-trained vision-language models for training effective data-limited generation models. KD-DLGAN consists of two innovative designs. The first is"},"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":"2303.17158","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-30T05:36:06Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"6299bafac762d6e11faa4a24e4836517e24c6508a460445b733f73a9096f4fbb","abstract_canon_sha256":"b57fb2a88bbb2bcdba81cbce8ce07fca3b48659efd3f961c91b8bfdc78bab5dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:20.341509Z","signature_b64":"r+ZVQgbr7BbIi3SwYBzU4xnNNNFB1hXdhGaGmpPMjHfESu41w7jaaj7eMfC1+mqJ2cBvp0g8iIbogsk3syUPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2a12aae77de7840d07520a4c643e33bea55c0a0852de6cf789bf96d9af5d621","last_reissued_at":"2026-07-05T05:56:20.341056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:20.341056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KD-DLGAN: Data Limited Image Generation via Knowledge Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Eric Xing, Fangneng Zhan, Kaiwen Cui, Shengcai Liao, Shijian Lu1, Yingchen Yu","submitted_at":"2023-03-30T05:36:06Z","abstract_excerpt":"Generative Adversarial Networks (GANs) rely heavily on large-scale training data for training high-quality image generation models. With limited training data, the GAN discriminator often suffers from severe overfitting which directly leads to degraded generation especially in generation diversity. Inspired by the recent advances in knowledge distillation (KD), we propose KD-DLGAN, a knowledge-distillation based generation framework that introduces pre-trained vision-language models for training effective data-limited generation models. KD-DLGAN consists of two innovative designs. The first is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17158","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/2303.17158/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":"2303.17158","created_at":"2026-07-05T05:56:20.341114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17158v1","created_at":"2026-07-05T05:56:20.341114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17158","created_at":"2026-07-05T05:56:20.341114+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KQSVLTX3Z4E","created_at":"2026-07-05T05:56:20.341114+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KQSVLTX3Z4EBUDV","created_at":"2026-07-05T05:56:20.341114+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KQSVLTX","created_at":"2026-07-05T05:56:20.341114+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/6KQSVLTX3Z4EBUDVECSMMQ7DHP","json":"https://pith.science/pith/6KQSVLTX3Z4EBUDVECSMMQ7DHP.json","graph_json":"https://pith.science/api/pith-number/6KQSVLTX3Z4EBUDVECSMMQ7DHP/graph.json","events_json":"https://pith.science/api/pith-number/6KQSVLTX3Z4EBUDVECSMMQ7DHP/events.json","paper":"https://pith.science/paper/6KQSVLTX"},"agent_actions":{"view_html":"https://pith.science/pith/6KQSVLTX3Z4EBUDVECSMMQ7DHP","download_json":"https://pith.science/pith/6KQSVLTX3Z4EBUDVECSMMQ7DHP.json","view_paper":"https://pith.science/paper/6KQSVLTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17158&json=true","fetch_graph":"https://pith.science/api/pith-number/6KQSVLTX3Z4EBUDVECSMMQ7DHP/graph.json","fetch_events":"https://pith.science/api/pith-number/6KQSVLTX3Z4EBUDVECSMMQ7DHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KQSVLTX3Z4EBUDVECSMMQ7DHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KQSVLTX3Z4EBUDVECSMMQ7DHP/action/storage_attestation","attest_author":"https://pith.science/pith/6KQSVLTX3Z4EBUDVECSMMQ7DHP/action/author_attestation","sign_citation":"https://pith.science/pith/6KQSVLTX3Z4EBUDVECSMMQ7DHP/action/citation_signature","submit_replication":"https://pith.science/pith/6KQSVLTX3Z4EBUDVECSMMQ7DHP/action/replication_record"}},"created_at":"2026-07-05T05:56:20.341114+00:00","updated_at":"2026-07-05T05:56:20.341114+00:00"}