{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IRZHE24LTM3BPGHUXG2LY5OVOI","short_pith_number":"pith:IRZHE24L","schema_version":"1.0","canonical_sha256":"4472726b8b9b361798f4b9b4bc75d572275c9639a80aa2de6e19d18663eb3386","source":{"kind":"arxiv","id":"2001.07926","version":1},"attestation_state":"computed","paper":{"title":"Optimized Generic Feature Learning for Few-shot Classification across Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Thomas Brox, Tonmoy Saikia","submitted_at":"2020-01-22T09:31:39Z","abstract_excerpt":"To learn models or features that generalize across tasks and domains is one of the grand goals of machine learning. In this paper, we propose to use cross-domain, cross-task data as validation objective for hyper-parameter optimization (HPO) to improve on this goal. Given a rich enough search space, optimization of hyper-parameters learn features that maximize validation performance and, due to the objective, generalize across tasks and domains. We demonstrate the effectiveness of this strategy on few-shot image classification within and across domains. The learned features outperform all prev"},"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":"2001.07926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-22T09:31:39Z","cross_cats_sorted":[],"title_canon_sha256":"e0ed0cf561de153f93d1d1d311e8e9e48e3bb100017a768591f791659f76788f","abstract_canon_sha256":"ddec8c19c82d5e360069c8325e1fe1690901a2db219eda65c9f7f884cd2add17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:06.218439Z","signature_b64":"Go9pZogr/jh/EU9Fi3k+rmO4DvQJidtWaq8uocOFm6VtlLh5f36Qib1yfL4zlddJWaSzihPxyd9H34X4WAnaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4472726b8b9b361798f4b9b4bc75d572275c9639a80aa2de6e19d18663eb3386","last_reissued_at":"2026-07-05T00:35:06.217933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:06.217933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimized Generic Feature Learning for Few-shot Classification across Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cordelia Schmid, Thomas Brox, Tonmoy Saikia","submitted_at":"2020-01-22T09:31:39Z","abstract_excerpt":"To learn models or features that generalize across tasks and domains is one of the grand goals of machine learning. In this paper, we propose to use cross-domain, cross-task data as validation objective for hyper-parameter optimization (HPO) to improve on this goal. Given a rich enough search space, optimization of hyper-parameters learn features that maximize validation performance and, due to the objective, generalize across tasks and domains. We demonstrate the effectiveness of this strategy on few-shot image classification within and across domains. The learned features outperform all prev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07926","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/2001.07926/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":"2001.07926","created_at":"2026-07-05T00:35:06.217990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.07926v1","created_at":"2026-07-05T00:35:06.217990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07926","created_at":"2026-07-05T00:35:06.217990+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRZHE24LTM3B","created_at":"2026-07-05T00:35:06.217990+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRZHE24LTM3BPGHU","created_at":"2026-07-05T00:35:06.217990+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRZHE24L","created_at":"2026-07-05T00:35:06.217990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00401","citing_title":"Few-shot Classification as Multi-instance Verification: Effective Backbone-agnostic Transfer across Domains","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRZHE24LTM3BPGHUXG2LY5OVOI","json":"https://pith.science/pith/IRZHE24LTM3BPGHUXG2LY5OVOI.json","graph_json":"https://pith.science/api/pith-number/IRZHE24LTM3BPGHUXG2LY5OVOI/graph.json","events_json":"https://pith.science/api/pith-number/IRZHE24LTM3BPGHUXG2LY5OVOI/events.json","paper":"https://pith.science/paper/IRZHE24L"},"agent_actions":{"view_html":"https://pith.science/pith/IRZHE24LTM3BPGHUXG2LY5OVOI","download_json":"https://pith.science/pith/IRZHE24LTM3BPGHUXG2LY5OVOI.json","view_paper":"https://pith.science/paper/IRZHE24L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.07926&json=true","fetch_graph":"https://pith.science/api/pith-number/IRZHE24LTM3BPGHUXG2LY5OVOI/graph.json","fetch_events":"https://pith.science/api/pith-number/IRZHE24LTM3BPGHUXG2LY5OVOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRZHE24LTM3BPGHUXG2LY5OVOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRZHE24LTM3BPGHUXG2LY5OVOI/action/storage_attestation","attest_author":"https://pith.science/pith/IRZHE24LTM3BPGHUXG2LY5OVOI/action/author_attestation","sign_citation":"https://pith.science/pith/IRZHE24LTM3BPGHUXG2LY5OVOI/action/citation_signature","submit_replication":"https://pith.science/pith/IRZHE24LTM3BPGHUXG2LY5OVOI/action/replication_record"}},"created_at":"2026-07-05T00:35:06.217990+00:00","updated_at":"2026-07-05T00:35:06.217990+00:00"}