{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BP737LFJV6IIP3QFWTUYJ3NHN2","short_pith_number":"pith:BP737LFJ","schema_version":"1.0","canonical_sha256":"0bffbfaca9af9087ee05b4e984eda76e8469f7538f4f26ce367b500505030d63","source":{"kind":"arxiv","id":"2211.03264","version":3},"attestation_state":"computed","paper":{"title":"Few-shot Image Generation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huimin Ma, Jiansheng Chen, Jian Yuan, Jingyuan Zhu","submitted_at":"2022-11-07T02:18:27Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPMs) have been proven capable of synthesizing high-quality images with remarkable diversity when trained on large amounts of data. However, to our knowledge, few-shot image generation tasks have yet to be studied with DDPM-based approaches. Modern approaches are mainly built on Generative Adversarial Networks (GANs) and adapt models pre-trained on large source domains to target domains using a few available samples. In this paper, we make the first attempt to study when do DDPMs overfit and suffer severe diversity degradation as training data become "},"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":"2211.03264","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-07T02:18:27Z","cross_cats_sorted":[],"title_canon_sha256":"560fc98437fcf5e473b949cc527e7418cd706fd3c4bae22f016ba72ee098485a","abstract_canon_sha256":"91961a6e0446ca74cbffcc4afbdccbd4178c5b1806784a24a25c424702e124ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:41.763886Z","signature_b64":"ilIYdJBbHZpjvjk57jkfAP3MttMv/Ci6zhNeeg9xcrMzCQtz3qQ3v0adxd+QD3ItIMBAsZRRpM2ROz6Ca8YTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bffbfaca9af9087ee05b4e984eda76e8469f7538f4f26ce367b500505030d63","last_reissued_at":"2026-07-05T05:48:41.763439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:41.763439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-shot Image Generation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huimin Ma, Jiansheng Chen, Jian Yuan, Jingyuan Zhu","submitted_at":"2022-11-07T02:18:27Z","abstract_excerpt":"Denoising diffusion probabilistic models (DDPMs) have been proven capable of synthesizing high-quality images with remarkable diversity when trained on large amounts of data. However, to our knowledge, few-shot image generation tasks have yet to be studied with DDPM-based approaches. Modern approaches are mainly built on Generative Adversarial Networks (GANs) and adapt models pre-trained on large source domains to target domains using a few available samples. In this paper, we make the first attempt to study when do DDPMs overfit and suffer severe diversity degradation as training data become "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03264","kind":"arxiv","version":3},"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/2211.03264/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":"2211.03264","created_at":"2026-07-05T05:48:41.763498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.03264v3","created_at":"2026-07-05T05:48:41.763498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03264","created_at":"2026-07-05T05:48:41.763498+00:00"},{"alias_kind":"pith_short_12","alias_value":"BP737LFJV6II","created_at":"2026-07-05T05:48:41.763498+00:00"},{"alias_kind":"pith_short_16","alias_value":"BP737LFJV6IIP3QF","created_at":"2026-07-05T05:48:41.763498+00:00"},{"alias_kind":"pith_short_8","alias_value":"BP737LFJ","created_at":"2026-07-05T05:48:41.763498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02532","citing_title":"Improving Combined Detection and Classification of TEM Defects via Mask-Conditioned Latent Diffusion Augmentation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16558","citing_title":"Cross-Modal Generation: From Commodity WiFi to High-Fidelity mmWave and RFID Sensing","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BP737LFJV6IIP3QFWTUYJ3NHN2","json":"https://pith.science/pith/BP737LFJV6IIP3QFWTUYJ3NHN2.json","graph_json":"https://pith.science/api/pith-number/BP737LFJV6IIP3QFWTUYJ3NHN2/graph.json","events_json":"https://pith.science/api/pith-number/BP737LFJV6IIP3QFWTUYJ3NHN2/events.json","paper":"https://pith.science/paper/BP737LFJ"},"agent_actions":{"view_html":"https://pith.science/pith/BP737LFJV6IIP3QFWTUYJ3NHN2","download_json":"https://pith.science/pith/BP737LFJV6IIP3QFWTUYJ3NHN2.json","view_paper":"https://pith.science/paper/BP737LFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.03264&json=true","fetch_graph":"https://pith.science/api/pith-number/BP737LFJV6IIP3QFWTUYJ3NHN2/graph.json","fetch_events":"https://pith.science/api/pith-number/BP737LFJV6IIP3QFWTUYJ3NHN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BP737LFJV6IIP3QFWTUYJ3NHN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BP737LFJV6IIP3QFWTUYJ3NHN2/action/storage_attestation","attest_author":"https://pith.science/pith/BP737LFJV6IIP3QFWTUYJ3NHN2/action/author_attestation","sign_citation":"https://pith.science/pith/BP737LFJV6IIP3QFWTUYJ3NHN2/action/citation_signature","submit_replication":"https://pith.science/pith/BP737LFJV6IIP3QFWTUYJ3NHN2/action/replication_record"}},"created_at":"2026-07-05T05:48:41.763498+00:00","updated_at":"2026-07-05T05:48:41.763498+00:00"}