{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Y4IHDOE4C26TDDB5OSGAQGEDSH","short_pith_number":"pith:Y4IHDOE4","schema_version":"1.0","canonical_sha256":"c71071b89c16bd318c3d748c08188391e7d7c1fa401807b9f94ec0ce7f2bfba1","source":{"kind":"arxiv","id":"2303.09677","version":1},"attestation_state":"computed","paper":{"title":"Instance-Conditioned GAN Data Augmentation for Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adriana Romero-Soriano, Arantxa Casanova, Jakob Verbeek, Michal Drozdzal, Pascal Vincent, Pietro Astolfi","submitted_at":"2023-03-16T22:45:43Z","abstract_excerpt":"Data augmentation has become a crucial component to train state-of-the-art visual representation models. However, handcrafting combinations of transformations that lead to improved performances is a laborious task, which can result in visually unrealistic samples. To overcome these limitations, recent works have explored the use of generative models as learnable data augmentation tools, showing promising results in narrow application domains, e.g., few-shot learning and low-data medical imaging. In this paper, we introduce a data augmentation module, called DA_IC-GAN, which leverages instance-"},"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":"2303.09677","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T22:45:43Z","cross_cats_sorted":[],"title_canon_sha256":"23f614d519f24bec34026338788066309273db1047db903f9a4f32f1e3a0de7d","abstract_canon_sha256":"1d3266308920157ec56aec9372eb789b51cd63045d9299853b51b50699d674e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:59.536182Z","signature_b64":"JQpWZksnu87SZ8jZfki0zLWLuPKw7+OJdXYnKOos2qTvtT+TmdwXyn39jz5xi8wWNJi6o6BqznepG/rjgHpfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c71071b89c16bd318c3d748c08188391e7d7c1fa401807b9f94ec0ce7f2bfba1","last_reissued_at":"2026-07-05T05:51:59.535667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:59.535667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instance-Conditioned GAN Data Augmentation for Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adriana Romero-Soriano, Arantxa Casanova, Jakob Verbeek, Michal Drozdzal, Pascal Vincent, Pietro Astolfi","submitted_at":"2023-03-16T22:45:43Z","abstract_excerpt":"Data augmentation has become a crucial component to train state-of-the-art visual representation models. However, handcrafting combinations of transformations that lead to improved performances is a laborious task, which can result in visually unrealistic samples. To overcome these limitations, recent works have explored the use of generative models as learnable data augmentation tools, showing promising results in narrow application domains, e.g., few-shot learning and low-data medical imaging. In this paper, we introduce a data augmentation module, called DA_IC-GAN, which leverages instance-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09677","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/2303.09677/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":"2303.09677","created_at":"2026-07-05T05:51:59.535743+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09677v1","created_at":"2026-07-05T05:51:59.535743+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09677","created_at":"2026-07-05T05:51:59.535743+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4IHDOE4C26T","created_at":"2026-07-05T05:51:59.535743+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4IHDOE4C26TDDB5","created_at":"2026-07-05T05:51:59.535743+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4IHDOE4","created_at":"2026-07-05T05:51:59.535743+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/Y4IHDOE4C26TDDB5OSGAQGEDSH","json":"https://pith.science/pith/Y4IHDOE4C26TDDB5OSGAQGEDSH.json","graph_json":"https://pith.science/api/pith-number/Y4IHDOE4C26TDDB5OSGAQGEDSH/graph.json","events_json":"https://pith.science/api/pith-number/Y4IHDOE4C26TDDB5OSGAQGEDSH/events.json","paper":"https://pith.science/paper/Y4IHDOE4"},"agent_actions":{"view_html":"https://pith.science/pith/Y4IHDOE4C26TDDB5OSGAQGEDSH","download_json":"https://pith.science/pith/Y4IHDOE4C26TDDB5OSGAQGEDSH.json","view_paper":"https://pith.science/paper/Y4IHDOE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09677&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4IHDOE4C26TDDB5OSGAQGEDSH/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4IHDOE4C26TDDB5OSGAQGEDSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4IHDOE4C26TDDB5OSGAQGEDSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4IHDOE4C26TDDB5OSGAQGEDSH/action/storage_attestation","attest_author":"https://pith.science/pith/Y4IHDOE4C26TDDB5OSGAQGEDSH/action/author_attestation","sign_citation":"https://pith.science/pith/Y4IHDOE4C26TDDB5OSGAQGEDSH/action/citation_signature","submit_replication":"https://pith.science/pith/Y4IHDOE4C26TDDB5OSGAQGEDSH/action/replication_record"}},"created_at":"2026-07-05T05:51:59.535743+00:00","updated_at":"2026-07-05T05:51:59.535743+00:00"}