{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:YZZVZBRA7REFTZE7BWTHK37FAG","short_pith_number":"pith:YZZVZBRA","schema_version":"1.0","canonical_sha256":"c6735c8620fc4859e49f0da6756fe501afcbaab43d9d9c093a352366b74b1863","source":{"kind":"arxiv","id":"1512.05227","version":2},"attestation_state":"computed","paper":{"title":"Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhou, Serge Belongie, Yin Cui, Yuanqing Lin","submitted_at":"2015-12-16T16:14:22Z","abstract_excerpt":"Existing fine-grained visual categorization methods often suffer from three challenges: lack of training data, large number of fine-grained categories, and high intraclass vs. low inter-class variance. In this work we propose a generic iterative framework for fine-grained categorization and dataset bootstrapping that handles these three challenges. Using deep metric learning with humans in the loop, we learn a low dimensional feature embedding with anchor points on manifolds for each category. These anchor points capture intra-class variances and remain discriminative between classes. In each "},"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":"1512.05227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-16T16:14:22Z","cross_cats_sorted":[],"title_canon_sha256":"1daa6017b5698e10a49de249b8ac559d87ac0d600da427339593728481ab4918","abstract_canon_sha256":"64f1708c618dfc5019f365ad0c32de46ff21e5cdd231b648cb79ab309ba4dbb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:24.852496Z","signature_b64":"FSbbct1CCpHfoV4vJDszS5wigN0/L0HvEokEu23xW1CGjS7s+/Ohsb82H1c7eoC9/kpMBoNG3wTuOlD7cUtnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6735c8620fc4859e49f0da6756fe501afcbaab43d9d9c093a352366b74b1863","last_reissued_at":"2026-05-18T01:17:24.851898Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:24.851898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhou, Serge Belongie, Yin Cui, Yuanqing Lin","submitted_at":"2015-12-16T16:14:22Z","abstract_excerpt":"Existing fine-grained visual categorization methods often suffer from three challenges: lack of training data, large number of fine-grained categories, and high intraclass vs. low inter-class variance. In this work we propose a generic iterative framework for fine-grained categorization and dataset bootstrapping that handles these three challenges. Using deep metric learning with humans in the loop, we learn a low dimensional feature embedding with anchor points on manifolds for each category. These anchor points capture intra-class variances and remain discriminative between classes. In each "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.05227","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":""},"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":"1512.05227","created_at":"2026-05-18T01:17:24.851980+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.05227v2","created_at":"2026-05-18T01:17:24.851980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.05227","created_at":"2026-05-18T01:17:24.851980+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZZVZBRA7REF","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZZVZBRA7REFTZE7","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZZVZBRA","created_at":"2026-05-18T12:29:52.810259+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/YZZVZBRA7REFTZE7BWTHK37FAG","json":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG.json","graph_json":"https://pith.science/api/pith-number/YZZVZBRA7REFTZE7BWTHK37FAG/graph.json","events_json":"https://pith.science/api/pith-number/YZZVZBRA7REFTZE7BWTHK37FAG/events.json","paper":"https://pith.science/paper/YZZVZBRA"},"agent_actions":{"view_html":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG","download_json":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG.json","view_paper":"https://pith.science/paper/YZZVZBRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.05227&json=true","fetch_graph":"https://pith.science/api/pith-number/YZZVZBRA7REFTZE7BWTHK37FAG/graph.json","fetch_events":"https://pith.science/api/pith-number/YZZVZBRA7REFTZE7BWTHK37FAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG/action/storage_attestation","attest_author":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG/action/author_attestation","sign_citation":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG/action/citation_signature","submit_replication":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG/action/replication_record"}},"created_at":"2026-05-18T01:17:24.851980+00:00","updated_at":"2026-05-18T01:17:24.851980+00:00"}