{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZBM5DXO6KK4FEXEXSJHB777TGF","short_pith_number":"pith:ZBM5DXO6","schema_version":"1.0","canonical_sha256":"c859d1ddde52b8525c97924e1ffff331791f9d53aa69aeecbd8b8e0b61170ef8","source":{"kind":"arxiv","id":"2205.09995","version":1},"attestation_state":"computed","paper":{"title":"Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhe Li, Changying Li, Dajiang Zhu, David Weizhong Liu, Haixing Dai, Lin Zhao, Lu Zhang, Tianming Liu, Tuo Zhang, Xi Jiang, Yuzhong Chen, Zhenxiang Xiao, Zihao Wu","submitted_at":"2022-05-20T07:25:33Z","abstract_excerpt":"Learning with little data is challenging but often inevitable in various application scenarios where the labeled data is limited and costly. Recently, few-shot learning (FSL) gained increasing attention because of its generalizability of prior knowledge to new tasks that contain only a few samples. However, for data-intensive models such as vision transformer (ViT), current fine-tuning based FSL approaches are inefficient in knowledge generalization and thus degenerate the downstream task performances. In this paper, we propose a novel mask-guided vision transformer (MG-ViT) to achieve an effe"},"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":"2205.09995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-20T07:25:33Z","cross_cats_sorted":[],"title_canon_sha256":"98752827f44409819d759fd9ef4ce88696597106057f337f7697a6bedb0ef151","abstract_canon_sha256":"23d8c6a621ed3225b7d63eef786bfc97e6fc12bc8695cc1c7839ae1dca5ab603"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:02.312673Z","signature_b64":"u9KCpfLBD7YwJV3RoSMqNVke/lROQKx3ANKuP1UhSfYjVWyhqjohaNj1Y4qjfnfGGT8CqlaMmva97EQ/xP1ZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c859d1ddde52b8525c97924e1ffff331791f9d53aa69aeecbd8b8e0b61170ef8","last_reissued_at":"2026-07-05T04:25:02.312215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:02.312215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhe Li, Changying Li, Dajiang Zhu, David Weizhong Liu, Haixing Dai, Lin Zhao, Lu Zhang, Tianming Liu, Tuo Zhang, Xi Jiang, Yuzhong Chen, Zhenxiang Xiao, Zihao Wu","submitted_at":"2022-05-20T07:25:33Z","abstract_excerpt":"Learning with little data is challenging but often inevitable in various application scenarios where the labeled data is limited and costly. Recently, few-shot learning (FSL) gained increasing attention because of its generalizability of prior knowledge to new tasks that contain only a few samples. However, for data-intensive models such as vision transformer (ViT), current fine-tuning based FSL approaches are inefficient in knowledge generalization and thus degenerate the downstream task performances. In this paper, we propose a novel mask-guided vision transformer (MG-ViT) to achieve an effe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09995","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/2205.09995/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":"2205.09995","created_at":"2026-07-05T04:25:02.312271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.09995v1","created_at":"2026-07-05T04:25:02.312271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09995","created_at":"2026-07-05T04:25:02.312271+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBM5DXO6KK4F","created_at":"2026-07-05T04:25:02.312271+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBM5DXO6KK4FEXEX","created_at":"2026-07-05T04:25:02.312271+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBM5DXO6","created_at":"2026-07-05T04:25:02.312271+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/ZBM5DXO6KK4FEXEXSJHB777TGF","json":"https://pith.science/pith/ZBM5DXO6KK4FEXEXSJHB777TGF.json","graph_json":"https://pith.science/api/pith-number/ZBM5DXO6KK4FEXEXSJHB777TGF/graph.json","events_json":"https://pith.science/api/pith-number/ZBM5DXO6KK4FEXEXSJHB777TGF/events.json","paper":"https://pith.science/paper/ZBM5DXO6"},"agent_actions":{"view_html":"https://pith.science/pith/ZBM5DXO6KK4FEXEXSJHB777TGF","download_json":"https://pith.science/pith/ZBM5DXO6KK4FEXEXSJHB777TGF.json","view_paper":"https://pith.science/paper/ZBM5DXO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.09995&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBM5DXO6KK4FEXEXSJHB777TGF/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBM5DXO6KK4FEXEXSJHB777TGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBM5DXO6KK4FEXEXSJHB777TGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBM5DXO6KK4FEXEXSJHB777TGF/action/storage_attestation","attest_author":"https://pith.science/pith/ZBM5DXO6KK4FEXEXSJHB777TGF/action/author_attestation","sign_citation":"https://pith.science/pith/ZBM5DXO6KK4FEXEXSJHB777TGF/action/citation_signature","submit_replication":"https://pith.science/pith/ZBM5DXO6KK4FEXEXSJHB777TGF/action/replication_record"}},"created_at":"2026-07-05T04:25:02.312271+00:00","updated_at":"2026-07-05T04:25:02.312271+00:00"}