{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3DHQCCKPNC3B3MDDBAZJTAIXTD","short_pith_number":"pith:3DHQCCKP","schema_version":"1.0","canonical_sha256":"d8cf01094f68b61db063083299811798d31045a0ef1e8238abf1cc0b622a2c00","source":{"kind":"arxiv","id":"2110.09446","version":1},"attestation_state":"computed","paper":{"title":"Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"St\\'ephane Pateux, Vincent Gripon, Yuqing Hu","submitted_at":"2021-10-18T16:29:17Z","abstract_excerpt":"Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed with the common aim of transferring knowledge acquired on a previously solved task, what is often achieved by using a pretrained feature extractor. Following this vein, in this paper we propose a novel transfer-based method which aims at processing the feature vectors so that they become closer to Gaussian-like distributions, resulting in increased accuracy. In the case of transductive few-shot learning where unlabelled test sample"},"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":"2110.09446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-18T16:29:17Z","cross_cats_sorted":[],"title_canon_sha256":"401aba39aa4deb5cdf6f78925af2a680e0d9bbbab9f8a02af1718a64959e8ee1","abstract_canon_sha256":"22b6d52f0861c0bed6b3e9362d3c5401ea42509afff5744df2fffbb3da3a65ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:28.367725Z","signature_b64":"zqohGD60okqmtVoU1hezn79YH3Wl7kCRwBvgQQOqHXSQzM8DAIVfV2LkrGE7dSk84UM8vom+K5n5NAT0jZEyDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8cf01094f68b61db063083299811798d31045a0ef1e8238abf1cc0b622a2c00","last_reissued_at":"2026-07-05T03:23:28.367344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:28.367344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"St\\'ephane Pateux, Vincent Gripon, Yuqing Hu","submitted_at":"2021-10-18T16:29:17Z","abstract_excerpt":"Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed with the common aim of transferring knowledge acquired on a previously solved task, what is often achieved by using a pretrained feature extractor. Following this vein, in this paper we propose a novel transfer-based method which aims at processing the feature vectors so that they become closer to Gaussian-like distributions, resulting in increased accuracy. In the case of transductive few-shot learning where unlabelled test sample"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09446","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/2110.09446/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":"2110.09446","created_at":"2026-07-05T03:23:28.367399+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.09446v1","created_at":"2026-07-05T03:23:28.367399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09446","created_at":"2026-07-05T03:23:28.367399+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DHQCCKPNC3B","created_at":"2026-07-05T03:23:28.367399+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DHQCCKPNC3B3MDD","created_at":"2026-07-05T03:23:28.367399+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DHQCCKP","created_at":"2026-07-05T03:23:28.367399+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/3DHQCCKPNC3B3MDDBAZJTAIXTD","json":"https://pith.science/pith/3DHQCCKPNC3B3MDDBAZJTAIXTD.json","graph_json":"https://pith.science/api/pith-number/3DHQCCKPNC3B3MDDBAZJTAIXTD/graph.json","events_json":"https://pith.science/api/pith-number/3DHQCCKPNC3B3MDDBAZJTAIXTD/events.json","paper":"https://pith.science/paper/3DHQCCKP"},"agent_actions":{"view_html":"https://pith.science/pith/3DHQCCKPNC3B3MDDBAZJTAIXTD","download_json":"https://pith.science/pith/3DHQCCKPNC3B3MDDBAZJTAIXTD.json","view_paper":"https://pith.science/paper/3DHQCCKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.09446&json=true","fetch_graph":"https://pith.science/api/pith-number/3DHQCCKPNC3B3MDDBAZJTAIXTD/graph.json","fetch_events":"https://pith.science/api/pith-number/3DHQCCKPNC3B3MDDBAZJTAIXTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DHQCCKPNC3B3MDDBAZJTAIXTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DHQCCKPNC3B3MDDBAZJTAIXTD/action/storage_attestation","attest_author":"https://pith.science/pith/3DHQCCKPNC3B3MDDBAZJTAIXTD/action/author_attestation","sign_citation":"https://pith.science/pith/3DHQCCKPNC3B3MDDBAZJTAIXTD/action/citation_signature","submit_replication":"https://pith.science/pith/3DHQCCKPNC3B3MDDBAZJTAIXTD/action/replication_record"}},"created_at":"2026-07-05T03:23:28.367399+00:00","updated_at":"2026-07-05T03:23:28.367399+00:00"}