{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DYLDQN5YKY6F46RZ7XCPIPNQ6L","short_pith_number":"pith:DYLDQN5Y","schema_version":"1.0","canonical_sha256":"1e163837b8563c5e7a39fdc4f43db0f2f29d8817f8933d8d64e1036a7c787147","source":{"kind":"arxiv","id":"2402.18331","version":3},"attestation_state":"computed","paper":{"title":"FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 Classes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feihong He, Gang Li, Kun Wang, Yongxuan Lai, Ziying Pan","submitted_at":"2024-02-28T13:50:46Z","abstract_excerpt":"The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A more challenging task, large-scale fine-grained image generation, remains the boundary to explore. In this work, we present a parameter-efficient strategy, called FineDiffusion, to fine-tune large pre-trained diffusion models scaling to large-scale fine-grained image generation with 10,000 categories. FineDiffusion significantly accelerates training and red"},"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":"2402.18331","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-28T13:50:46Z","cross_cats_sorted":[],"title_canon_sha256":"c9c682e7903a134b5ed9aca83ff79bf5d26dd504c3913af50b69205522d75b0f","abstract_canon_sha256":"ef68f3e6c18aefdb8800290a7572a0b5d73130b7b6e3b6741c470e333db47631"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:04.934281Z","signature_b64":"cCv5U0vUXOdupzXJsNoM7Db5/QiaTKIu5C67X4hMx+S94FZ9qErfdzNdIdSDeN5hYcxdI7BeUY8+epNc3WjCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e163837b8563c5e7a39fdc4f43db0f2f29d8817f8933d8d64e1036a7c787147","last_reissued_at":"2026-07-05T08:27:04.933880Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:04.933880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 Classes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feihong He, Gang Li, Kun Wang, Yongxuan Lai, Ziying Pan","submitted_at":"2024-02-28T13:50:46Z","abstract_excerpt":"The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A more challenging task, large-scale fine-grained image generation, remains the boundary to explore. In this work, we present a parameter-efficient strategy, called FineDiffusion, to fine-tune large pre-trained diffusion models scaling to large-scale fine-grained image generation with 10,000 categories. FineDiffusion significantly accelerates training and red"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18331","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/2402.18331/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":"2402.18331","created_at":"2026-07-05T08:27:04.933935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18331v3","created_at":"2026-07-05T08:27:04.933935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18331","created_at":"2026-07-05T08:27:04.933935+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYLDQN5YKY6F","created_at":"2026-07-05T08:27:04.933935+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYLDQN5YKY6F46RZ","created_at":"2026-07-05T08:27:04.933935+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYLDQN5Y","created_at":"2026-07-05T08:27:04.933935+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/DYLDQN5YKY6F46RZ7XCPIPNQ6L","json":"https://pith.science/pith/DYLDQN5YKY6F46RZ7XCPIPNQ6L.json","graph_json":"https://pith.science/api/pith-number/DYLDQN5YKY6F46RZ7XCPIPNQ6L/graph.json","events_json":"https://pith.science/api/pith-number/DYLDQN5YKY6F46RZ7XCPIPNQ6L/events.json","paper":"https://pith.science/paper/DYLDQN5Y"},"agent_actions":{"view_html":"https://pith.science/pith/DYLDQN5YKY6F46RZ7XCPIPNQ6L","download_json":"https://pith.science/pith/DYLDQN5YKY6F46RZ7XCPIPNQ6L.json","view_paper":"https://pith.science/paper/DYLDQN5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18331&json=true","fetch_graph":"https://pith.science/api/pith-number/DYLDQN5YKY6F46RZ7XCPIPNQ6L/graph.json","fetch_events":"https://pith.science/api/pith-number/DYLDQN5YKY6F46RZ7XCPIPNQ6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYLDQN5YKY6F46RZ7XCPIPNQ6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYLDQN5YKY6F46RZ7XCPIPNQ6L/action/storage_attestation","attest_author":"https://pith.science/pith/DYLDQN5YKY6F46RZ7XCPIPNQ6L/action/author_attestation","sign_citation":"https://pith.science/pith/DYLDQN5YKY6F46RZ7XCPIPNQ6L/action/citation_signature","submit_replication":"https://pith.science/pith/DYLDQN5YKY6F46RZ7XCPIPNQ6L/action/replication_record"}},"created_at":"2026-07-05T08:27:04.933935+00:00","updated_at":"2026-07-05T08:27:04.933935+00:00"}