{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RP4IKYRLAYDNVASVJESEN5HJLI","short_pith_number":"pith:RP4IKYRL","schema_version":"1.0","canonical_sha256":"8bf885622b0606da8255492446f4e95a0e4ae3f0cd900642fb4f9fe1d1331571","source":{"kind":"arxiv","id":"2107.02341","version":3},"attestation_state":"computed","paper":{"title":"Feature Fusion Vision Transformer for Fine-Grained Visual Categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Wang, Xiaohan Yu, Yongsheng Gao","submitted_at":"2021-07-06T01:48:43Z","abstract_excerpt":"The core for tackling the fine-grained visual categorization (FGVC) is to learn subtle yet discriminative features. Most previous works achieve this by explicitly selecting the discriminative parts or integrating the attention mechanism via CNN-based approaches.However, these methods enhance the computational complexity and make the modeldominated by the regions containing the most of the objects. Recently, vision trans-former (ViT) has achieved SOTA performance on general image recognition tasks. Theself-attention mechanism aggregates and weights the information from all patches to the classi"},"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":"2107.02341","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-06T01:48:43Z","cross_cats_sorted":[],"title_canon_sha256":"915bda5f0f566c19300ec9bfdb59463d0bf220b7f16607b6f86df7359111e4ec","abstract_canon_sha256":"8777cac94d5446ffbacb6a8e8143043b9060cf748414c4fa52aa5f49e4fdee19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:54.435322Z","signature_b64":"8Ip7N75SKuV0zpH+uekKZQ9yxA6InHuVtUXNbNVPZbQP1MiGWuG4/XBfoywImqeA6VCunhwgjnBs7EsPoqqqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bf885622b0606da8255492446f4e95a0e4ae3f0cd900642fb4f9fe1d1331571","last_reissued_at":"2026-07-05T04:00:54.434823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:54.434823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Fusion Vision Transformer for Fine-Grained Visual Categorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Wang, Xiaohan Yu, Yongsheng Gao","submitted_at":"2021-07-06T01:48:43Z","abstract_excerpt":"The core for tackling the fine-grained visual categorization (FGVC) is to learn subtle yet discriminative features. Most previous works achieve this by explicitly selecting the discriminative parts or integrating the attention mechanism via CNN-based approaches.However, these methods enhance the computational complexity and make the modeldominated by the regions containing the most of the objects. Recently, vision trans-former (ViT) has achieved SOTA performance on general image recognition tasks. Theself-attention mechanism aggregates and weights the information from all patches to the classi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02341","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/2107.02341/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":"2107.02341","created_at":"2026-07-05T04:00:54.434877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.02341v3","created_at":"2026-07-05T04:00:54.434877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02341","created_at":"2026-07-05T04:00:54.434877+00:00"},{"alias_kind":"pith_short_12","alias_value":"RP4IKYRLAYDN","created_at":"2026-07-05T04:00:54.434877+00:00"},{"alias_kind":"pith_short_16","alias_value":"RP4IKYRLAYDNVASV","created_at":"2026-07-05T04:00:54.434877+00:00"},{"alias_kind":"pith_short_8","alias_value":"RP4IKYRL","created_at":"2026-07-05T04:00:54.434877+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/RP4IKYRLAYDNVASVJESEN5HJLI","json":"https://pith.science/pith/RP4IKYRLAYDNVASVJESEN5HJLI.json","graph_json":"https://pith.science/api/pith-number/RP4IKYRLAYDNVASVJESEN5HJLI/graph.json","events_json":"https://pith.science/api/pith-number/RP4IKYRLAYDNVASVJESEN5HJLI/events.json","paper":"https://pith.science/paper/RP4IKYRL"},"agent_actions":{"view_html":"https://pith.science/pith/RP4IKYRLAYDNVASVJESEN5HJLI","download_json":"https://pith.science/pith/RP4IKYRLAYDNVASVJESEN5HJLI.json","view_paper":"https://pith.science/paper/RP4IKYRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.02341&json=true","fetch_graph":"https://pith.science/api/pith-number/RP4IKYRLAYDNVASVJESEN5HJLI/graph.json","fetch_events":"https://pith.science/api/pith-number/RP4IKYRLAYDNVASVJESEN5HJLI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RP4IKYRLAYDNVASVJESEN5HJLI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RP4IKYRLAYDNVASVJESEN5HJLI/action/storage_attestation","attest_author":"https://pith.science/pith/RP4IKYRLAYDNVASVJESEN5HJLI/action/author_attestation","sign_citation":"https://pith.science/pith/RP4IKYRLAYDNVASVJESEN5HJLI/action/citation_signature","submit_replication":"https://pith.science/pith/RP4IKYRLAYDNVASVJESEN5HJLI/action/replication_record"}},"created_at":"2026-07-05T04:00:54.434877+00:00","updated_at":"2026-07-05T04:00:54.434877+00:00"}