{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IQX3PEEWGBCV4CUHZRELGYOQZR","short_pith_number":"pith:IQX3PEEW","schema_version":"1.0","canonical_sha256":"442fb7909630455e0a87cc48b361d0cc43802315a106e5298e399d6d43487e97","source":{"kind":"arxiv","id":"2203.09064","version":1},"attestation_state":"computed","paper":{"title":"Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongyang Zhao, Hong-Yu Zhou, Weifeng Ge, Weihan Liang, Wenqiang Zhang, Yangji He, Yizhou Yu","submitted_at":"2022-03-17T03:49:58Z","abstract_excerpt":"This paper presents new hierarchically cascaded transformers that can improve data efficiency through attribute surrogates learning and spectral tokens pooling. Vision transformers have recently been thought of as a promising alternative to convolutional neural networks for visual recognition. But when there is no sufficient data, it gets stuck in overfitting and shows inferior performance. To improve data efficiency, we propose hierarchically cascaded transformers that exploit intrinsic image structures through spectral tokens pooling and optimize the learnable parameters through latent attri"},"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":"2203.09064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-17T03:49:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"903159e9e05fae23893b020a0cb32261cb7c19942485f44863bd7a3fe121c5b8","abstract_canon_sha256":"870358bf33169dbbf537ad93a81328ab8357dac3f35a063e8df74644cdd5403f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:06.792198Z","signature_b64":"bLillPrgdFicXSzbA+8TWgxRnpY/k49xi8KPF1uPr+S2DpmWue34uMSvD9AtjBmx24kRTlm2HJicGSOnV4QyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"442fb7909630455e0a87cc48b361d0cc43802315a106e5298e399d6d43487e97","last_reissued_at":"2026-07-05T04:06:06.791692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:06.791692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dongyang Zhao, Hong-Yu Zhou, Weifeng Ge, Weihan Liang, Wenqiang Zhang, Yangji He, Yizhou Yu","submitted_at":"2022-03-17T03:49:58Z","abstract_excerpt":"This paper presents new hierarchically cascaded transformers that can improve data efficiency through attribute surrogates learning and spectral tokens pooling. Vision transformers have recently been thought of as a promising alternative to convolutional neural networks for visual recognition. But when there is no sufficient data, it gets stuck in overfitting and shows inferior performance. To improve data efficiency, we propose hierarchically cascaded transformers that exploit intrinsic image structures through spectral tokens pooling and optimize the learnable parameters through latent attri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09064","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/2203.09064/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":"2203.09064","created_at":"2026-07-05T04:06:06.791766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.09064v1","created_at":"2026-07-05T04:06:06.791766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09064","created_at":"2026-07-05T04:06:06.791766+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQX3PEEWGBCV","created_at":"2026-07-05T04:06:06.791766+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQX3PEEWGBCV4CUH","created_at":"2026-07-05T04:06:06.791766+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQX3PEEW","created_at":"2026-07-05T04:06:06.791766+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/IQX3PEEWGBCV4CUHZRELGYOQZR","json":"https://pith.science/pith/IQX3PEEWGBCV4CUHZRELGYOQZR.json","graph_json":"https://pith.science/api/pith-number/IQX3PEEWGBCV4CUHZRELGYOQZR/graph.json","events_json":"https://pith.science/api/pith-number/IQX3PEEWGBCV4CUHZRELGYOQZR/events.json","paper":"https://pith.science/paper/IQX3PEEW"},"agent_actions":{"view_html":"https://pith.science/pith/IQX3PEEWGBCV4CUHZRELGYOQZR","download_json":"https://pith.science/pith/IQX3PEEWGBCV4CUHZRELGYOQZR.json","view_paper":"https://pith.science/paper/IQX3PEEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.09064&json=true","fetch_graph":"https://pith.science/api/pith-number/IQX3PEEWGBCV4CUHZRELGYOQZR/graph.json","fetch_events":"https://pith.science/api/pith-number/IQX3PEEWGBCV4CUHZRELGYOQZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQX3PEEWGBCV4CUHZRELGYOQZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQX3PEEWGBCV4CUHZRELGYOQZR/action/storage_attestation","attest_author":"https://pith.science/pith/IQX3PEEWGBCV4CUHZRELGYOQZR/action/author_attestation","sign_citation":"https://pith.science/pith/IQX3PEEWGBCV4CUHZRELGYOQZR/action/citation_signature","submit_replication":"https://pith.science/pith/IQX3PEEWGBCV4CUHZRELGYOQZR/action/replication_record"}},"created_at":"2026-07-05T04:06:06.791766+00:00","updated_at":"2026-07-05T04:06:06.791766+00:00"}