{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RF2UVMTN2VP4LEXSETA7HWIVG3","short_pith_number":"pith:RF2UVMTN","schema_version":"1.0","canonical_sha256":"89754ab26dd55fc592f224c1f3d91536c6f259bc43c4a6c3ed40fe4da0b132db","source":{"kind":"arxiv","id":"2005.08463","version":3},"attestation_state":"computed","paper":{"title":"Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyu Liu, Jianan Jiang, Jieping Ye, Yuhong Guo, Zhenpeng Li, Zhen Zhao","submitted_at":"2020-05-18T05:31:04Z","abstract_excerpt":"In this paper, we propose a feature transformation ensemble model with batch spectral regularization for the Cross-domain few-shot learning (CD-FSL) challenge. Specifically, we proposes to construct an ensemble prediction model by performing diverse feature transformations after a feature extraction network. On each branch prediction network of the model we use a batch spectral regularization term to suppress the singular values of the feature matrix during pre-training to improve the generalization ability of the model. The proposed model can then be fine tuned in the target domain to address"},"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":"2005.08463","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-18T05:31:04Z","cross_cats_sorted":[],"title_canon_sha256":"1ae0053096002df0afbc38c0a9db6cb79ca1400e7da963d9052828d65115f02a","abstract_canon_sha256":"62dcdc2c568f4806cae3304d4027caeb3e3c861273527e4ab80189a35a278e22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:04:52.276874Z","signature_b64":"N9i2UBqDIAtzbEi23O6shp2Gxk/kujajALxGjXj/Q/gj1YE5I5mwWZoY9+xs+QTr+1kc9gz44ENa2bsX3I0xDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89754ab26dd55fc592f224c1f3d91536c6f259bc43c4a6c3ed40fe4da0b132db","last_reissued_at":"2026-07-05T01:04:52.276432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:04:52.276432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyu Liu, Jianan Jiang, Jieping Ye, Yuhong Guo, Zhenpeng Li, Zhen Zhao","submitted_at":"2020-05-18T05:31:04Z","abstract_excerpt":"In this paper, we propose a feature transformation ensemble model with batch spectral regularization for the Cross-domain few-shot learning (CD-FSL) challenge. Specifically, we proposes to construct an ensemble prediction model by performing diverse feature transformations after a feature extraction network. On each branch prediction network of the model we use a batch spectral regularization term to suppress the singular values of the feature matrix during pre-training to improve the generalization ability of the model. The proposed model can then be fine tuned in the target domain to address"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08463","kind":"arxiv","version":3},"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/2005.08463/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":"2005.08463","created_at":"2026-07-05T01:04:52.276496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.08463v3","created_at":"2026-07-05T01:04:52.276496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08463","created_at":"2026-07-05T01:04:52.276496+00:00"},{"alias_kind":"pith_short_12","alias_value":"RF2UVMTN2VP4","created_at":"2026-07-05T01:04:52.276496+00:00"},{"alias_kind":"pith_short_16","alias_value":"RF2UVMTN2VP4LEXS","created_at":"2026-07-05T01:04:52.276496+00:00"},{"alias_kind":"pith_short_8","alias_value":"RF2UVMTN","created_at":"2026-07-05T01:04:52.276496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15506","citing_title":"Prompt Tuning Vision Language Models with Margin Regularizer for Few-Shot Learning under Distribution Shifts","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RF2UVMTN2VP4LEXSETA7HWIVG3","json":"https://pith.science/pith/RF2UVMTN2VP4LEXSETA7HWIVG3.json","graph_json":"https://pith.science/api/pith-number/RF2UVMTN2VP4LEXSETA7HWIVG3/graph.json","events_json":"https://pith.science/api/pith-number/RF2UVMTN2VP4LEXSETA7HWIVG3/events.json","paper":"https://pith.science/paper/RF2UVMTN"},"agent_actions":{"view_html":"https://pith.science/pith/RF2UVMTN2VP4LEXSETA7HWIVG3","download_json":"https://pith.science/pith/RF2UVMTN2VP4LEXSETA7HWIVG3.json","view_paper":"https://pith.science/paper/RF2UVMTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.08463&json=true","fetch_graph":"https://pith.science/api/pith-number/RF2UVMTN2VP4LEXSETA7HWIVG3/graph.json","fetch_events":"https://pith.science/api/pith-number/RF2UVMTN2VP4LEXSETA7HWIVG3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RF2UVMTN2VP4LEXSETA7HWIVG3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RF2UVMTN2VP4LEXSETA7HWIVG3/action/storage_attestation","attest_author":"https://pith.science/pith/RF2UVMTN2VP4LEXSETA7HWIVG3/action/author_attestation","sign_citation":"https://pith.science/pith/RF2UVMTN2VP4LEXSETA7HWIVG3/action/citation_signature","submit_replication":"https://pith.science/pith/RF2UVMTN2VP4LEXSETA7HWIVG3/action/replication_record"}},"created_at":"2026-07-05T01:04:52.276496+00:00","updated_at":"2026-07-05T01:04:52.276496+00:00"}