{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DKIDNN4ILYXIH3UA6ZTEIV7FYK","short_pith_number":"pith:DKIDNN4I","schema_version":"1.0","canonical_sha256":"1a9036b7885e2e83ee80f6664457e5c2912fa9d034074d9e5cf4fcdbfbb9ea60","source":{"kind":"arxiv","id":"2410.14749","version":1},"attestation_state":"computed","paper":{"title":"CFTS-GAN: Continual Few-Shot Teacher Student for Generative Adversarial Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Leonardo Rossi, Massimo Bertozzi, Munsif Ali","submitted_at":"2024-10-17T20:49:08Z","abstract_excerpt":"Few-shot and continual learning face two well-known challenges in GANs: overfitting and catastrophic forgetting. Learning new tasks results in catastrophic forgetting in deep learning models. In the case of a few-shot setting, the model learns from a very limited number of samples (e.g. 10 samples), which can lead to overfitting and mode collapse. So, this paper proposes a Continual Few-shot Teacher-Student technique for the generative adversarial network (CFTS-GAN) that considers both challenges together. Our CFTS-GAN uses an adapter module as a student to learn a new task without affecting t"},"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":"2410.14749","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T20:49:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2daa6e13fd8997410602b8e1f8e49d55997d6993f8b80697fe198069ffda237b","abstract_canon_sha256":"ae2b390145af66372379b56b82472394076174502150a2d6f9dff1b4d2c33e14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:15.937462Z","signature_b64":"+GlJchVEP5jW0AhX9we+jIhAMJtHrNhV6HBGeRdC3JSsZID5U8kqWotpCh2JjAZniJOd0Rx8Le3e+Oc2dhlvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a9036b7885e2e83ee80f6664457e5c2912fa9d034074d9e5cf4fcdbfbb9ea60","last_reissued_at":"2026-07-05T09:23:15.936996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:15.936996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CFTS-GAN: Continual Few-Shot Teacher Student for Generative Adversarial Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Leonardo Rossi, Massimo Bertozzi, Munsif Ali","submitted_at":"2024-10-17T20:49:08Z","abstract_excerpt":"Few-shot and continual learning face two well-known challenges in GANs: overfitting and catastrophic forgetting. Learning new tasks results in catastrophic forgetting in deep learning models. In the case of a few-shot setting, the model learns from a very limited number of samples (e.g. 10 samples), which can lead to overfitting and mode collapse. So, this paper proposes a Continual Few-shot Teacher-Student technique for the generative adversarial network (CFTS-GAN) that considers both challenges together. Our CFTS-GAN uses an adapter module as a student to learn a new task without affecting t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14749","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/2410.14749/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":"2410.14749","created_at":"2026-07-05T09:23:15.937056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14749v1","created_at":"2026-07-05T09:23:15.937056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14749","created_at":"2026-07-05T09:23:15.937056+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKIDNN4ILYXI","created_at":"2026-07-05T09:23:15.937056+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKIDNN4ILYXIH3UA","created_at":"2026-07-05T09:23:15.937056+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKIDNN4I","created_at":"2026-07-05T09:23:15.937056+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/DKIDNN4ILYXIH3UA6ZTEIV7FYK","json":"https://pith.science/pith/DKIDNN4ILYXIH3UA6ZTEIV7FYK.json","graph_json":"https://pith.science/api/pith-number/DKIDNN4ILYXIH3UA6ZTEIV7FYK/graph.json","events_json":"https://pith.science/api/pith-number/DKIDNN4ILYXIH3UA6ZTEIV7FYK/events.json","paper":"https://pith.science/paper/DKIDNN4I"},"agent_actions":{"view_html":"https://pith.science/pith/DKIDNN4ILYXIH3UA6ZTEIV7FYK","download_json":"https://pith.science/pith/DKIDNN4ILYXIH3UA6ZTEIV7FYK.json","view_paper":"https://pith.science/paper/DKIDNN4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14749&json=true","fetch_graph":"https://pith.science/api/pith-number/DKIDNN4ILYXIH3UA6ZTEIV7FYK/graph.json","fetch_events":"https://pith.science/api/pith-number/DKIDNN4ILYXIH3UA6ZTEIV7FYK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKIDNN4ILYXIH3UA6ZTEIV7FYK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKIDNN4ILYXIH3UA6ZTEIV7FYK/action/storage_attestation","attest_author":"https://pith.science/pith/DKIDNN4ILYXIH3UA6ZTEIV7FYK/action/author_attestation","sign_citation":"https://pith.science/pith/DKIDNN4ILYXIH3UA6ZTEIV7FYK/action/citation_signature","submit_replication":"https://pith.science/pith/DKIDNN4ILYXIH3UA6ZTEIV7FYK/action/replication_record"}},"created_at":"2026-07-05T09:23:15.937056+00:00","updated_at":"2026-07-05T09:23:15.937056+00:00"}