{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AEGWUFGXZXMMLCHHPNPWL5JQ6B","short_pith_number":"pith:AEGWUFGX","schema_version":"1.0","canonical_sha256":"010d6a14d7cdd8c588e77b5f65f530f07a3389ee0eb1eb8d8f7931fda2f0021e","source":{"kind":"arxiv","id":"1909.02729","version":5},"attestation_state":"computed","paper":{"title":"A Baseline for Few-Shot Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Avinash Ravichandran, Guneet S. Dhillon, Pratik Chaudhari, Stefano Soatto","submitted_at":"2019-09-06T06:14:03Z","abstract_excerpt":"Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet, Tiered-ImageNet, CIFAR-FS and FC-100 with the same hyper-parameters. The simplicity of this approach enables us to demonstrate the first few-shot learning results on the ImageNet-21k dataset. We find that using a large number of meta-training classes results in high few-shot accuracies even for a large number of few-shot classes. We do not advocate our approac"},"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":"1909.02729","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-06T06:14:03Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"454d0ea853261d1be763b0386903039d1fbe258570b5eeae5fd5b9966686231f","abstract_canon_sha256":"83f37fe6cebc1e968c46fd64155d2a4b06824120b61a98b2bf9f8d73ee5baad0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:01.723255Z","signature_b64":"jrAIV3O4ShJ/B+AK1nCe3h0QRnIOTqA9lkaQL0Kbfp2/J2VKhWrGeVqaJ7zY0FUp52hm5RUGV+erquiq9sdjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"010d6a14d7cdd8c588e77b5f65f530f07a3389ee0eb1eb8d8f7931fda2f0021e","last_reissued_at":"2026-07-05T01:45:01.722847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:01.722847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Baseline for Few-Shot Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Avinash Ravichandran, Guneet S. Dhillon, Pratik Chaudhari, Stefano Soatto","submitted_at":"2019-09-06T06:14:03Z","abstract_excerpt":"Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet, Tiered-ImageNet, CIFAR-FS and FC-100 with the same hyper-parameters. The simplicity of this approach enables us to demonstrate the first few-shot learning results on the ImageNet-21k dataset. We find that using a large number of meta-training classes results in high few-shot accuracies even for a large number of few-shot classes. We do not advocate our approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02729","kind":"arxiv","version":5},"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/1909.02729/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":"1909.02729","created_at":"2026-07-05T01:45:01.722901+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.02729v5","created_at":"2026-07-05T01:45:01.722901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02729","created_at":"2026-07-05T01:45:01.722901+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEGWUFGXZXMM","created_at":"2026-07-05T01:45:01.722901+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEGWUFGXZXMMLCHH","created_at":"2026-07-05T01:45:01.722901+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEGWUFGX","created_at":"2026-07-05T01:45:01.722901+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":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AEGWUFGXZXMMLCHHPNPWL5JQ6B","json":"https://pith.science/pith/AEGWUFGXZXMMLCHHPNPWL5JQ6B.json","graph_json":"https://pith.science/api/pith-number/AEGWUFGXZXMMLCHHPNPWL5JQ6B/graph.json","events_json":"https://pith.science/api/pith-number/AEGWUFGXZXMMLCHHPNPWL5JQ6B/events.json","paper":"https://pith.science/paper/AEGWUFGX"},"agent_actions":{"view_html":"https://pith.science/pith/AEGWUFGXZXMMLCHHPNPWL5JQ6B","download_json":"https://pith.science/pith/AEGWUFGXZXMMLCHHPNPWL5JQ6B.json","view_paper":"https://pith.science/paper/AEGWUFGX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.02729&json=true","fetch_graph":"https://pith.science/api/pith-number/AEGWUFGXZXMMLCHHPNPWL5JQ6B/graph.json","fetch_events":"https://pith.science/api/pith-number/AEGWUFGXZXMMLCHHPNPWL5JQ6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEGWUFGXZXMMLCHHPNPWL5JQ6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEGWUFGXZXMMLCHHPNPWL5JQ6B/action/storage_attestation","attest_author":"https://pith.science/pith/AEGWUFGXZXMMLCHHPNPWL5JQ6B/action/author_attestation","sign_citation":"https://pith.science/pith/AEGWUFGXZXMMLCHHPNPWL5JQ6B/action/citation_signature","submit_replication":"https://pith.science/pith/AEGWUFGXZXMMLCHHPNPWL5JQ6B/action/replication_record"}},"created_at":"2026-07-05T01:45:01.722901+00:00","updated_at":"2026-07-05T01:45:01.722901+00:00"}