{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ER37RR3N4NOFPLML5W4G6LRQKV","short_pith_number":"pith:ER37RR3N","schema_version":"1.0","canonical_sha256":"2477f8c76de35c57ad8bedb86f2e305569213082f9bdbfb8e6364aee6535b614","source":{"kind":"arxiv","id":"1911.04623","version":2},"attestation_state":"computed","paper":{"title":"SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kilian Q. Weinberger, Laurens van der Maaten, Wei-Lun Chao, Yan Wang","submitted_at":"2019-11-12T00:44:10Z","abstract_excerpt":"Few-shot learners aim to recognize new object classes based on a small number of labeled training examples. To prevent overfitting, state-of-the-art few-shot learners use meta-learning on convolutional-network features and perform classification using a nearest-neighbor classifier. This paper studies the accuracy of nearest-neighbor baselines without meta-learning. Surprisingly, we find simple feature transformations suffice to obtain competitive few-shot learning accuracies. For example, we find that a nearest-neighbor classifier used in combination with mean-subtraction and L2-normalization "},"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":"1911.04623","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-12T00:44:10Z","cross_cats_sorted":[],"title_canon_sha256":"12cfb77f077b5afad691cf7afba9600224648746fc860d1d21a40db033798721","abstract_canon_sha256":"de983e5a928ddb8be318c427c0ec31b17896c00f04c988bfdecec92252b2adf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:38.965859Z","signature_b64":"/lV3uW8nFMtxdFhQB1obnaRJLHta1Mq/KnYJ/H2S3H4PODqOfO+hYdUeAaGI3sPADiOFT426RZyQno4RNIXbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2477f8c76de35c57ad8bedb86f2e305569213082f9bdbfb8e6364aee6535b614","last_reissued_at":"2026-07-05T00:19:38.965375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:38.965375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kilian Q. Weinberger, Laurens van der Maaten, Wei-Lun Chao, Yan Wang","submitted_at":"2019-11-12T00:44:10Z","abstract_excerpt":"Few-shot learners aim to recognize new object classes based on a small number of labeled training examples. To prevent overfitting, state-of-the-art few-shot learners use meta-learning on convolutional-network features and perform classification using a nearest-neighbor classifier. This paper studies the accuracy of nearest-neighbor baselines without meta-learning. Surprisingly, we find simple feature transformations suffice to obtain competitive few-shot learning accuracies. For example, we find that a nearest-neighbor classifier used in combination with mean-subtraction and L2-normalization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.04623","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/1911.04623/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":"1911.04623","created_at":"2026-07-05T00:19:38.965435+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.04623v2","created_at":"2026-07-05T00:19:38.965435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.04623","created_at":"2026-07-05T00:19:38.965435+00:00"},{"alias_kind":"pith_short_12","alias_value":"ER37RR3N4NOF","created_at":"2026-07-05T00:19:38.965435+00:00"},{"alias_kind":"pith_short_16","alias_value":"ER37RR3N4NOFPLML","created_at":"2026-07-05T00:19:38.965435+00:00"},{"alias_kind":"pith_short_8","alias_value":"ER37RR3N","created_at":"2026-07-05T00:19:38.965435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27538","citing_title":"Self-Supervised Learning of Plant Image Representations","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02779","citing_title":"3D Foundation Model for Generalizable Disease Detection in Head Computed Tomography","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02667","citing_title":"Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11710","citing_title":"Unlocking Compositional Generalization in Continual Few-Shot Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2510.18326","citing_title":"Enhancing Few-Shot Classification of Benchmark and Disaster Imagery with ABHFA-Net","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11710","citing_title":"Unlocking Compositional Generalization in Continual Few-Shot Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27538","citing_title":"Self-Supervised Learning of Plant Image Representations","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05034","citing_title":"Few-Shot Learning Pipeline for Monkeypox Skin Disease Classification Using CNN Feature Extractors","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05480","citing_title":"Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22031","citing_title":"Mochi: Aligning Pre-training and Inference for Efficient Graph Foundation Models via Meta-Learning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ER37RR3N4NOFPLML5W4G6LRQKV","json":"https://pith.science/pith/ER37RR3N4NOFPLML5W4G6LRQKV.json","graph_json":"https://pith.science/api/pith-number/ER37RR3N4NOFPLML5W4G6LRQKV/graph.json","events_json":"https://pith.science/api/pith-number/ER37RR3N4NOFPLML5W4G6LRQKV/events.json","paper":"https://pith.science/paper/ER37RR3N"},"agent_actions":{"view_html":"https://pith.science/pith/ER37RR3N4NOFPLML5W4G6LRQKV","download_json":"https://pith.science/pith/ER37RR3N4NOFPLML5W4G6LRQKV.json","view_paper":"https://pith.science/paper/ER37RR3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.04623&json=true","fetch_graph":"https://pith.science/api/pith-number/ER37RR3N4NOFPLML5W4G6LRQKV/graph.json","fetch_events":"https://pith.science/api/pith-number/ER37RR3N4NOFPLML5W4G6LRQKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ER37RR3N4NOFPLML5W4G6LRQKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ER37RR3N4NOFPLML5W4G6LRQKV/action/storage_attestation","attest_author":"https://pith.science/pith/ER37RR3N4NOFPLML5W4G6LRQKV/action/author_attestation","sign_citation":"https://pith.science/pith/ER37RR3N4NOFPLML5W4G6LRQKV/action/citation_signature","submit_replication":"https://pith.science/pith/ER37RR3N4NOFPLML5W4G6LRQKV/action/replication_record"}},"created_at":"2026-07-05T00:19:38.965435+00:00","updated_at":"2026-07-05T00:19:38.965435+00:00"}