{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FJXCTMDL4BV5ZFVT24FRI5I6XU","short_pith_number":"pith:FJXCTMDL","schema_version":"1.0","canonical_sha256":"2a6e29b06be06bdc96b3d70b14751ebd04a4de63f414e33de2c672a5003f54f9","source":{"kind":"arxiv","id":"2008.02465","version":2},"attestation_state":"computed","paper":{"title":"Few-shot Classification via Adaptive Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Kang, Jiashi Feng, Kuangqi Zhou, Zihang Jiang","submitted_at":"2020-08-06T05:52:59Z","abstract_excerpt":"Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from two aspects, namely optimizing an initial model or learning a distance metric. In this work, we propose a novel few-shot learning method via optimizing and fast adapting the query sample representation based on very few reference samples. To be specific, we devise a simple and efficient meta-reweighting strategy to adapt the sample representations and gener"},"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":"2008.02465","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-06T05:52:59Z","cross_cats_sorted":[],"title_canon_sha256":"e822a9d39903bfa37decc8341b68dc2e5d071573327c4ae671a6caf1b6ba6770","abstract_canon_sha256":"124c4295ca60b5f7e92447dcad2188ecda9fee40029e73507be6a0c465bb1239"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:21.553806Z","signature_b64":"yCm6n0nwj51uq84sHU7dvFuaxUqUNh3QtHTsae64d1wRTpssP/AfbRQoOxqyEYZivoj+XtYjX09Sfu4zLbvlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a6e29b06be06bdc96b3d70b14751ebd04a4de63f414e33de2c672a5003f54f9","last_reissued_at":"2026-07-05T01:53:21.553304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:21.553304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-shot Classification via Adaptive Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Kang, Jiashi Feng, Kuangqi Zhou, Zihang Jiang","submitted_at":"2020-08-06T05:52:59Z","abstract_excerpt":"Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from two aspects, namely optimizing an initial model or learning a distance metric. In this work, we propose a novel few-shot learning method via optimizing and fast adapting the query sample representation based on very few reference samples. To be specific, we devise a simple and efficient meta-reweighting strategy to adapt the sample representations and gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02465","kind":"arxiv","version":2},"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/2008.02465/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":"2008.02465","created_at":"2026-07-05T01:53:21.553378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.02465v2","created_at":"2026-07-05T01:53:21.553378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02465","created_at":"2026-07-05T01:53:21.553378+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJXCTMDL4BV5","created_at":"2026-07-05T01:53:21.553378+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJXCTMDL4BV5ZFVT","created_at":"2026-07-05T01:53:21.553378+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJXCTMDL","created_at":"2026-07-05T01:53:21.553378+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.18326","citing_title":"Enhancing Few-Shot Classification of Benchmark and Disaster Imagery with ABHFA-Net","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FJXCTMDL4BV5ZFVT24FRI5I6XU","json":"https://pith.science/pith/FJXCTMDL4BV5ZFVT24FRI5I6XU.json","graph_json":"https://pith.science/api/pith-number/FJXCTMDL4BV5ZFVT24FRI5I6XU/graph.json","events_json":"https://pith.science/api/pith-number/FJXCTMDL4BV5ZFVT24FRI5I6XU/events.json","paper":"https://pith.science/paper/FJXCTMDL"},"agent_actions":{"view_html":"https://pith.science/pith/FJXCTMDL4BV5ZFVT24FRI5I6XU","download_json":"https://pith.science/pith/FJXCTMDL4BV5ZFVT24FRI5I6XU.json","view_paper":"https://pith.science/paper/FJXCTMDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.02465&json=true","fetch_graph":"https://pith.science/api/pith-number/FJXCTMDL4BV5ZFVT24FRI5I6XU/graph.json","fetch_events":"https://pith.science/api/pith-number/FJXCTMDL4BV5ZFVT24FRI5I6XU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJXCTMDL4BV5ZFVT24FRI5I6XU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJXCTMDL4BV5ZFVT24FRI5I6XU/action/storage_attestation","attest_author":"https://pith.science/pith/FJXCTMDL4BV5ZFVT24FRI5I6XU/action/author_attestation","sign_citation":"https://pith.science/pith/FJXCTMDL4BV5ZFVT24FRI5I6XU/action/citation_signature","submit_replication":"https://pith.science/pith/FJXCTMDL4BV5ZFVT24FRI5I6XU/action/replication_record"}},"created_at":"2026-07-05T01:53:21.553378+00:00","updated_at":"2026-07-05T01:53:21.553378+00:00"}