{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JHXG7J5IR3V7GWZPNFPKXLCDWW","short_pith_number":"pith:JHXG7J5I","schema_version":"1.0","canonical_sha256":"49ee6fa7a88eebf35b2f695eabac43b5941130354556537c495087852e036782","source":{"kind":"arxiv","id":"2101.04775","version":1},"attestation_state":"computed","paper":{"title":"Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmed Elgammal, Bingchen Liu, Kunpeng Song, Yizhe Zhu","submitted_at":"2021-01-12T22:02:54Z","abstract_excerpt":"Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires large-scale GPU-clusters and a vast number of training images. In this paper, we study the few-shot image synthesis task for GAN with minimum computing cost. We propose a light-weight GAN structure that gains superior quality on 1024*1024 resolution. Notably, the model converges from scratch with just a few hours of training on a single RTX-2080 GPU, and has a consistent performance, even with less than 100 training samples. Two technique designs constitute our work, a skip-layer channel-wise excitation mod"},"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":"2101.04775","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-12T22:02:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fefbf484f506e4e7bf8a2edbe1ec913e05be78dab9ad7874b47e3eb9c76e3d8a","abstract_canon_sha256":"47cf21e666e168b2ec2c4d2eb736def7058cdbec82be5debdf2db42cc484b274"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:34.696614Z","signature_b64":"IXMMXF02wkaHxYJ2p1xZ+eZBeC85+Gz5n+JvTwCKMRHhKphcZIBPQceMdHSoFEp3y27I6GEjkFrEVN5FQjuNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49ee6fa7a88eebf35b2f695eabac43b5941130354556537c495087852e036782","last_reissued_at":"2026-07-05T02:06:34.696185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:34.696185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmed Elgammal, Bingchen Liu, Kunpeng Song, Yizhe Zhu","submitted_at":"2021-01-12T22:02:54Z","abstract_excerpt":"Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires large-scale GPU-clusters and a vast number of training images. In this paper, we study the few-shot image synthesis task for GAN with minimum computing cost. We propose a light-weight GAN structure that gains superior quality on 1024*1024 resolution. Notably, the model converges from scratch with just a few hours of training on a single RTX-2080 GPU, and has a consistent performance, even with less than 100 training samples. Two technique designs constitute our work, a skip-layer channel-wise excitation mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.04775","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/2101.04775/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":"2101.04775","created_at":"2026-07-05T02:06:34.696250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.04775v1","created_at":"2026-07-05T02:06:34.696250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.04775","created_at":"2026-07-05T02:06:34.696250+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHXG7J5IR3V7","created_at":"2026-07-05T02:06:34.696250+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHXG7J5IR3V7GWZP","created_at":"2026-07-05T02:06:34.696250+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHXG7J5I","created_at":"2026-07-05T02:06:34.696250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01022","citing_title":"Workflow-Based Evaluation of Music Generation Systems","ref_index":90,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JHXG7J5IR3V7GWZPNFPKXLCDWW","json":"https://pith.science/pith/JHXG7J5IR3V7GWZPNFPKXLCDWW.json","graph_json":"https://pith.science/api/pith-number/JHXG7J5IR3V7GWZPNFPKXLCDWW/graph.json","events_json":"https://pith.science/api/pith-number/JHXG7J5IR3V7GWZPNFPKXLCDWW/events.json","paper":"https://pith.science/paper/JHXG7J5I"},"agent_actions":{"view_html":"https://pith.science/pith/JHXG7J5IR3V7GWZPNFPKXLCDWW","download_json":"https://pith.science/pith/JHXG7J5IR3V7GWZPNFPKXLCDWW.json","view_paper":"https://pith.science/paper/JHXG7J5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.04775&json=true","fetch_graph":"https://pith.science/api/pith-number/JHXG7J5IR3V7GWZPNFPKXLCDWW/graph.json","fetch_events":"https://pith.science/api/pith-number/JHXG7J5IR3V7GWZPNFPKXLCDWW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHXG7J5IR3V7GWZPNFPKXLCDWW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHXG7J5IR3V7GWZPNFPKXLCDWW/action/storage_attestation","attest_author":"https://pith.science/pith/JHXG7J5IR3V7GWZPNFPKXLCDWW/action/author_attestation","sign_citation":"https://pith.science/pith/JHXG7J5IR3V7GWZPNFPKXLCDWW/action/citation_signature","submit_replication":"https://pith.science/pith/JHXG7J5IR3V7GWZPNFPKXLCDWW/action/replication_record"}},"created_at":"2026-07-05T02:06:34.696250+00:00","updated_at":"2026-07-05T02:06:34.696250+00:00"}