{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5NW2RGZRY6NMPHVXKOZNJPVG2Q","short_pith_number":"pith:5NW2RGZR","schema_version":"1.0","canonical_sha256":"eb6da89b31c79ac79eb753b2d4bea6d404d45cb0870ebddfea774782665f25e4","source":{"kind":"arxiv","id":"2305.07102","version":1},"attestation_state":"computed","paper":{"title":"Salient Mask-Guided Vision Transformer for Fine-Grained Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aliakbar Abdurahimov, Dmitry Demidov, Fahad Shahbaz Khan, Hisham Cholakkal, Muhammad Hamza Sharif","submitted_at":"2023-05-11T19:24:33Z","abstract_excerpt":"Fine-grained visual classification (FGVC) is a challenging computer vision problem, where the task is to automatically recognise objects from subordinate categories. One of its main difficulties is capturing the most discriminative inter-class variances among visually similar classes. Recently, methods with Vision Transformer (ViT) have demonstrated noticeable achievements in FGVC, generally by employing the self-attention mechanism with additional resource-consuming techniques to distinguish potentially discriminative regions while disregarding the rest. However, such approaches may struggle "},"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":"2305.07102","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-11T19:24:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a1bf3e6296f560b18ee26665ae3765aa409eb3af20665fcc80850bb9182e0b6","abstract_canon_sha256":"36dda6bce7eda7c545a7fb6dd17b64092412b157d09bc6697cb448ecd25f6726"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:26.804397Z","signature_b64":"9PLau2cWZW6Q1kMcKO3wtHIA/YeYPx1LCxnS5fMINBGp/UDJq4/psIksuGV0Fyradsx1mEUUMH8sNAuKLbuBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb6da89b31c79ac79eb753b2d4bea6d404d45cb0870ebddfea774782665f25e4","last_reissued_at":"2026-07-05T07:29:26.803910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:26.803910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Salient Mask-Guided Vision Transformer for Fine-Grained Classification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aliakbar Abdurahimov, Dmitry Demidov, Fahad Shahbaz Khan, Hisham Cholakkal, Muhammad Hamza Sharif","submitted_at":"2023-05-11T19:24:33Z","abstract_excerpt":"Fine-grained visual classification (FGVC) is a challenging computer vision problem, where the task is to automatically recognise objects from subordinate categories. One of its main difficulties is capturing the most discriminative inter-class variances among visually similar classes. Recently, methods with Vision Transformer (ViT) have demonstrated noticeable achievements in FGVC, generally by employing the self-attention mechanism with additional resource-consuming techniques to distinguish potentially discriminative regions while disregarding the rest. However, such approaches may struggle "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07102","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/2305.07102/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":"2305.07102","created_at":"2026-07-05T07:29:26.803966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.07102v1","created_at":"2026-07-05T07:29:26.803966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07102","created_at":"2026-07-05T07:29:26.803966+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NW2RGZRY6NM","created_at":"2026-07-05T07:29:26.803966+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NW2RGZRY6NMPHVX","created_at":"2026-07-05T07:29:26.803966+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NW2RGZR","created_at":"2026-07-05T07:29:26.803966+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/5NW2RGZRY6NMPHVXKOZNJPVG2Q","json":"https://pith.science/pith/5NW2RGZRY6NMPHVXKOZNJPVG2Q.json","graph_json":"https://pith.science/api/pith-number/5NW2RGZRY6NMPHVXKOZNJPVG2Q/graph.json","events_json":"https://pith.science/api/pith-number/5NW2RGZRY6NMPHVXKOZNJPVG2Q/events.json","paper":"https://pith.science/paper/5NW2RGZR"},"agent_actions":{"view_html":"https://pith.science/pith/5NW2RGZRY6NMPHVXKOZNJPVG2Q","download_json":"https://pith.science/pith/5NW2RGZRY6NMPHVXKOZNJPVG2Q.json","view_paper":"https://pith.science/paper/5NW2RGZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.07102&json=true","fetch_graph":"https://pith.science/api/pith-number/5NW2RGZRY6NMPHVXKOZNJPVG2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/5NW2RGZRY6NMPHVXKOZNJPVG2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NW2RGZRY6NMPHVXKOZNJPVG2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NW2RGZRY6NMPHVXKOZNJPVG2Q/action/storage_attestation","attest_author":"https://pith.science/pith/5NW2RGZRY6NMPHVXKOZNJPVG2Q/action/author_attestation","sign_citation":"https://pith.science/pith/5NW2RGZRY6NMPHVXKOZNJPVG2Q/action/citation_signature","submit_replication":"https://pith.science/pith/5NW2RGZRY6NMPHVXKOZNJPVG2Q/action/replication_record"}},"created_at":"2026-07-05T07:29:26.803966+00:00","updated_at":"2026-07-05T07:29:26.803966+00:00"}