{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4V4TEXFPVB22NY4Y6ONZXYGEI6","short_pith_number":"pith:4V4TEXFP","schema_version":"1.0","canonical_sha256":"e579325cafa875a6e398f39b9be0c447a9208725a0ba35844a5c1ad00363cbbc","source":{"kind":"arxiv","id":"2208.12398","version":1},"attestation_state":"computed","paper":{"title":"Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Luo, Bo Jiang, Xiao Wang, Xixi Wang","submitted_at":"2022-08-26T01:53:23Z","abstract_excerpt":"Few-shot classification which aims to recognize unseen classes using very limited samples has attracted more and more attention. Usually, it is formulated as a metric learning problem. The core issue of few-shot classification is how to learn (1) consistent representations for images in both support and query sets and (2) effective metric learning for images between support and query sets. In this paper, we show that the two challenges can be well modeled simultaneously via a unified Query-Support TransFormer (QSFormer) model. To be specific,the proposed QSFormer involves global query-support "},"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":"2208.12398","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-26T01:53:23Z","cross_cats_sorted":[],"title_canon_sha256":"0c5ca950fefda8b31ed405ad408e3151066ea456d31386f202d495e2eaa6d7de","abstract_canon_sha256":"19a1cb84ead235bcc1092fd480d261fa385f54e59a5ea578fe4a864cf51048bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:44.741979Z","signature_b64":"Eg9AV57dWwGkS7llopJE7jmevRtZ456ogWU0TsKTNoCgpt6VfaQg2ATDZTeRltQYazLOTpJqZuSp2kabVenSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e579325cafa875a6e398f39b9be0c447a9208725a0ba35844a5c1ad00363cbbc","last_reissued_at":"2026-07-05T04:51:44.741636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:44.741636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Luo, Bo Jiang, Xiao Wang, Xixi Wang","submitted_at":"2022-08-26T01:53:23Z","abstract_excerpt":"Few-shot classification which aims to recognize unseen classes using very limited samples has attracted more and more attention. Usually, it is formulated as a metric learning problem. The core issue of few-shot classification is how to learn (1) consistent representations for images in both support and query sets and (2) effective metric learning for images between support and query sets. In this paper, we show that the two challenges can be well modeled simultaneously via a unified Query-Support TransFormer (QSFormer) model. To be specific,the proposed QSFormer involves global query-support "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.12398","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/2208.12398/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":"2208.12398","created_at":"2026-07-05T04:51:44.741695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.12398v1","created_at":"2026-07-05T04:51:44.741695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.12398","created_at":"2026-07-05T04:51:44.741695+00:00"},{"alias_kind":"pith_short_12","alias_value":"4V4TEXFPVB22","created_at":"2026-07-05T04:51:44.741695+00:00"},{"alias_kind":"pith_short_16","alias_value":"4V4TEXFPVB22NY4Y","created_at":"2026-07-05T04:51:44.741695+00:00"},{"alias_kind":"pith_short_8","alias_value":"4V4TEXFP","created_at":"2026-07-05T04:51:44.741695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09299","citing_title":"ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluation","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4V4TEXFPVB22NY4Y6ONZXYGEI6","json":"https://pith.science/pith/4V4TEXFPVB22NY4Y6ONZXYGEI6.json","graph_json":"https://pith.science/api/pith-number/4V4TEXFPVB22NY4Y6ONZXYGEI6/graph.json","events_json":"https://pith.science/api/pith-number/4V4TEXFPVB22NY4Y6ONZXYGEI6/events.json","paper":"https://pith.science/paper/4V4TEXFP"},"agent_actions":{"view_html":"https://pith.science/pith/4V4TEXFPVB22NY4Y6ONZXYGEI6","download_json":"https://pith.science/pith/4V4TEXFPVB22NY4Y6ONZXYGEI6.json","view_paper":"https://pith.science/paper/4V4TEXFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.12398&json=true","fetch_graph":"https://pith.science/api/pith-number/4V4TEXFPVB22NY4Y6ONZXYGEI6/graph.json","fetch_events":"https://pith.science/api/pith-number/4V4TEXFPVB22NY4Y6ONZXYGEI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4V4TEXFPVB22NY4Y6ONZXYGEI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4V4TEXFPVB22NY4Y6ONZXYGEI6/action/storage_attestation","attest_author":"https://pith.science/pith/4V4TEXFPVB22NY4Y6ONZXYGEI6/action/author_attestation","sign_citation":"https://pith.science/pith/4V4TEXFPVB22NY4Y6ONZXYGEI6/action/citation_signature","submit_replication":"https://pith.science/pith/4V4TEXFPVB22NY4Y6ONZXYGEI6/action/replication_record"}},"created_at":"2026-07-05T04:51:44.741695+00:00","updated_at":"2026-07-05T04:51:44.741695+00:00"}