{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VE2LT4CBEZ5P3ZVVHYZAIIVOXO","short_pith_number":"pith:VE2LT4CB","schema_version":"1.0","canonical_sha256":"a934b9f041267afde6b53e320422aebb9991028ac6e19ebef452e324e80f2a71","source":{"kind":"arxiv","id":"1806.04728","version":3},"attestation_state":"computed","paper":{"title":"RepMet: Representative-based metric learning for classification and one-shot object detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex M. Bronstein, Amit Aides, Eli Schwartz, Joseph Shtok, Leonid Karlinsky, Raja Giryes, Rogerio Feris, Sivan Harary","submitted_at":"2018-06-12T19:25:38Z","abstract_excerpt":"Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples. In this work, we propose a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process. Our approach outperforms state-of-the-art methods for DML-based object classification on a variety of standard fine-grained"},"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":"1806.04728","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-12T19:25:38Z","cross_cats_sorted":[],"title_canon_sha256":"d8185b1997260fa01ba51296a6ecb8fd214387d4b75bd6258f60c539a4977d3a","abstract_canon_sha256":"ab79faedd24841af8e0b84868b44f7d0d8255b1a9833392f82344064aceb172d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:30.175714Z","signature_b64":"X+v/CJ+dbxyaIWLYPevlV9fmq0NIdX3DEJ3j7ehSX3+f1OBw4xfZ2NeO07Fzc0MJLDqvQ4mB+qpeY3H7VGa+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a934b9f041267afde6b53e320422aebb9991028ac6e19ebef452e324e80f2a71","last_reissued_at":"2026-05-18T00:00:30.175249Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:30.175249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepMet: Representative-based metric learning for classification and one-shot object detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex M. Bronstein, Amit Aides, Eli Schwartz, Joseph Shtok, Leonid Karlinsky, Raja Giryes, Rogerio Feris, Sivan Harary","submitted_at":"2018-06-12T19:25:38Z","abstract_excerpt":"Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples. In this work, we propose a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process. Our approach outperforms state-of-the-art methods for DML-based object classification on a variety of standard fine-grained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04728","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":""},"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":"1806.04728","created_at":"2026-05-18T00:00:30.175329+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.04728v3","created_at":"2026-05-18T00:00:30.175329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04728","created_at":"2026-05-18T00:00:30.175329+00:00"},{"alias_kind":"pith_short_12","alias_value":"VE2LT4CBEZ5P","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VE2LT4CBEZ5P3ZVV","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VE2LT4CB","created_at":"2026-05-18T12:32:59.047623+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/VE2LT4CBEZ5P3ZVVHYZAIIVOXO","json":"https://pith.science/pith/VE2LT4CBEZ5P3ZVVHYZAIIVOXO.json","graph_json":"https://pith.science/api/pith-number/VE2LT4CBEZ5P3ZVVHYZAIIVOXO/graph.json","events_json":"https://pith.science/api/pith-number/VE2LT4CBEZ5P3ZVVHYZAIIVOXO/events.json","paper":"https://pith.science/paper/VE2LT4CB"},"agent_actions":{"view_html":"https://pith.science/pith/VE2LT4CBEZ5P3ZVVHYZAIIVOXO","download_json":"https://pith.science/pith/VE2LT4CBEZ5P3ZVVHYZAIIVOXO.json","view_paper":"https://pith.science/paper/VE2LT4CB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.04728&json=true","fetch_graph":"https://pith.science/api/pith-number/VE2LT4CBEZ5P3ZVVHYZAIIVOXO/graph.json","fetch_events":"https://pith.science/api/pith-number/VE2LT4CBEZ5P3ZVVHYZAIIVOXO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VE2LT4CBEZ5P3ZVVHYZAIIVOXO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VE2LT4CBEZ5P3ZVVHYZAIIVOXO/action/storage_attestation","attest_author":"https://pith.science/pith/VE2LT4CBEZ5P3ZVVHYZAIIVOXO/action/author_attestation","sign_citation":"https://pith.science/pith/VE2LT4CBEZ5P3ZVVHYZAIIVOXO/action/citation_signature","submit_replication":"https://pith.science/pith/VE2LT4CBEZ5P3ZVVHYZAIIVOXO/action/replication_record"}},"created_at":"2026-05-18T00:00:30.175329+00:00","updated_at":"2026-05-18T00:00:30.175329+00:00"}