{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HC32Y5CS4HOMYFYQMZO5AICJH4","short_pith_number":"pith:HC32Y5CS","schema_version":"1.0","canonical_sha256":"38b7ac7452e1dccc1710665dd020493f2bbdee6a945d868b3faec3208963dfad","source":{"kind":"arxiv","id":"2109.05719","version":1},"attestation_state":"computed","paper":{"title":"Fine-Grained Few Shot Learning with Foreground Object Transformation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofei Wang, Gao Huang, Qisen Yang, Shiji Song, Xiang Li","submitted_at":"2021-09-13T05:58:20Z","abstract_excerpt":"Traditional fine-grained image classification generally requires abundant labeled samples to deal with the low inter-class variance but high intra-class variance problem. However, in many scenarios we may have limited samples for some novel sub-categories, leading to the fine-grained few shot learning (FG-FSL) setting. To address this challenging task, we propose a novel method named foreground object transformation (FOT), which is composed of a foreground object extractor and a posture transformation generator. The former aims to remove image background, which tends to increase the difficulty"},"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":"2109.05719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T05:58:20Z","cross_cats_sorted":[],"title_canon_sha256":"f7c4f16ba1e4118d1ff2edb4c2c4134f13682f60edd660447efea09069e2e591","abstract_canon_sha256":"79c700b7f22418eb0b11ca5a7434bf6d54d6774c069a4b16c9c86cf883cc43b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:41.670636Z","signature_b64":"gnnZNa5c7OGCRRPvnyUpaR6oXlOC9wnsZ8quIq5R9+CLXFW8kgC9ck1JGdwAm2SKOZxSIOJcyWRvAuyWQCJIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38b7ac7452e1dccc1710665dd020493f2bbdee6a945d868b3faec3208963dfad","last_reissued_at":"2026-07-05T03:13:41.670238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:41.670238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Grained Few Shot Learning with Foreground Object Transformation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofei Wang, Gao Huang, Qisen Yang, Shiji Song, Xiang Li","submitted_at":"2021-09-13T05:58:20Z","abstract_excerpt":"Traditional fine-grained image classification generally requires abundant labeled samples to deal with the low inter-class variance but high intra-class variance problem. However, in many scenarios we may have limited samples for some novel sub-categories, leading to the fine-grained few shot learning (FG-FSL) setting. To address this challenging task, we propose a novel method named foreground object transformation (FOT), which is composed of a foreground object extractor and a posture transformation generator. The former aims to remove image background, which tends to increase the difficulty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05719","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/2109.05719/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":"2109.05719","created_at":"2026-07-05T03:13:41.670299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05719v1","created_at":"2026-07-05T03:13:41.670299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05719","created_at":"2026-07-05T03:13:41.670299+00:00"},{"alias_kind":"pith_short_12","alias_value":"HC32Y5CS4HOM","created_at":"2026-07-05T03:13:41.670299+00:00"},{"alias_kind":"pith_short_16","alias_value":"HC32Y5CS4HOMYFYQ","created_at":"2026-07-05T03:13:41.670299+00:00"},{"alias_kind":"pith_short_8","alias_value":"HC32Y5CS","created_at":"2026-07-05T03:13:41.670299+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/HC32Y5CS4HOMYFYQMZO5AICJH4","json":"https://pith.science/pith/HC32Y5CS4HOMYFYQMZO5AICJH4.json","graph_json":"https://pith.science/api/pith-number/HC32Y5CS4HOMYFYQMZO5AICJH4/graph.json","events_json":"https://pith.science/api/pith-number/HC32Y5CS4HOMYFYQMZO5AICJH4/events.json","paper":"https://pith.science/paper/HC32Y5CS"},"agent_actions":{"view_html":"https://pith.science/pith/HC32Y5CS4HOMYFYQMZO5AICJH4","download_json":"https://pith.science/pith/HC32Y5CS4HOMYFYQMZO5AICJH4.json","view_paper":"https://pith.science/paper/HC32Y5CS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05719&json=true","fetch_graph":"https://pith.science/api/pith-number/HC32Y5CS4HOMYFYQMZO5AICJH4/graph.json","fetch_events":"https://pith.science/api/pith-number/HC32Y5CS4HOMYFYQMZO5AICJH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HC32Y5CS4HOMYFYQMZO5AICJH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HC32Y5CS4HOMYFYQMZO5AICJH4/action/storage_attestation","attest_author":"https://pith.science/pith/HC32Y5CS4HOMYFYQMZO5AICJH4/action/author_attestation","sign_citation":"https://pith.science/pith/HC32Y5CS4HOMYFYQMZO5AICJH4/action/citation_signature","submit_replication":"https://pith.science/pith/HC32Y5CS4HOMYFYQMZO5AICJH4/action/replication_record"}},"created_at":"2026-07-05T03:13:41.670299+00:00","updated_at":"2026-07-05T03:13:41.670299+00:00"}