{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5TMUTC75BVUEI5I6MGRFDSOATV","short_pith_number":"pith:5TMUTC75","schema_version":"1.0","canonical_sha256":"ecd9498bfd0d6844751e61a251c9c09d48d24b4f9a6859c3169ca8177ab9015e","source":{"kind":"arxiv","id":"2312.03046","version":2},"attestation_state":"computed","paper":{"title":"Diversified in-domain synthesis with efficient fine-tuning for few-shot classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Nicola Dall'Asen, Nicu Sebe, Victor G. Turrisi da Costa, Yiming Wang","submitted_at":"2023-12-05T17:18:09Z","abstract_excerpt":"Few-shot image classification aims to learn an image classifier using only a small set of labeled examples per class. A recent research direction for improving few-shot classifiers involves augmenting the labelled samples with synthetic images created by state-of-the-art text-to-image generation models. Following this trend, we propose Diversified In-domain Synthesis with Efficient Fine-tuning (DISEF), a novel approach which addresses the generalization challenge in few-shot learning using synthetic data. DISEF consists of two main components. First, we propose a novel text-to-image augmentati"},"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":"2312.03046","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T17:18:09Z","cross_cats_sorted":[],"title_canon_sha256":"d3e58da09d819f3741ac190dbc274dd6aef235c807264f4827266faa7fa885db","abstract_canon_sha256":"fa1dcda3e12ae718a10b134e442c91298c79c277311ee7a52b76d20956980a9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:47.043197Z","signature_b64":"oBXBUpWg2qreYAWSfPwR/JmNkf3EFUfaAynoky9iq9bvquU1cWLPTfMBiEVgWf76sGy5msZnPz/IrckfJnCRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecd9498bfd0d6844751e61a251c9c09d48d24b4f9a6859c3169ca8177ab9015e","last_reissued_at":"2026-07-05T07:21:47.042737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:47.042737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diversified in-domain synthesis with efficient fine-tuning for few-shot classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Nicola Dall'Asen, Nicu Sebe, Victor G. Turrisi da Costa, Yiming Wang","submitted_at":"2023-12-05T17:18:09Z","abstract_excerpt":"Few-shot image classification aims to learn an image classifier using only a small set of labeled examples per class. A recent research direction for improving few-shot classifiers involves augmenting the labelled samples with synthetic images created by state-of-the-art text-to-image generation models. Following this trend, we propose Diversified In-domain Synthesis with Efficient Fine-tuning (DISEF), a novel approach which addresses the generalization challenge in few-shot learning using synthetic data. DISEF consists of two main components. First, we propose a novel text-to-image augmentati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03046","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/2312.03046/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":"2312.03046","created_at":"2026-07-05T07:21:47.042796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03046v2","created_at":"2026-07-05T07:21:47.042796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03046","created_at":"2026-07-05T07:21:47.042796+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TMUTC75BVUE","created_at":"2026-07-05T07:21:47.042796+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TMUTC75BVUEI5I6","created_at":"2026-07-05T07:21:47.042796+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TMUTC75","created_at":"2026-07-05T07:21:47.042796+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.14543","citing_title":"Exploring Cross-Modal Flows for Few-Shot Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5TMUTC75BVUEI5I6MGRFDSOATV","json":"https://pith.science/pith/5TMUTC75BVUEI5I6MGRFDSOATV.json","graph_json":"https://pith.science/api/pith-number/5TMUTC75BVUEI5I6MGRFDSOATV/graph.json","events_json":"https://pith.science/api/pith-number/5TMUTC75BVUEI5I6MGRFDSOATV/events.json","paper":"https://pith.science/paper/5TMUTC75"},"agent_actions":{"view_html":"https://pith.science/pith/5TMUTC75BVUEI5I6MGRFDSOATV","download_json":"https://pith.science/pith/5TMUTC75BVUEI5I6MGRFDSOATV.json","view_paper":"https://pith.science/paper/5TMUTC75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03046&json=true","fetch_graph":"https://pith.science/api/pith-number/5TMUTC75BVUEI5I6MGRFDSOATV/graph.json","fetch_events":"https://pith.science/api/pith-number/5TMUTC75BVUEI5I6MGRFDSOATV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TMUTC75BVUEI5I6MGRFDSOATV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TMUTC75BVUEI5I6MGRFDSOATV/action/storage_attestation","attest_author":"https://pith.science/pith/5TMUTC75BVUEI5I6MGRFDSOATV/action/author_attestation","sign_citation":"https://pith.science/pith/5TMUTC75BVUEI5I6MGRFDSOATV/action/citation_signature","submit_replication":"https://pith.science/pith/5TMUTC75BVUEI5I6MGRFDSOATV/action/replication_record"}},"created_at":"2026-07-05T07:21:47.042796+00:00","updated_at":"2026-07-05T07:21:47.042796+00:00"}