{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DE7Z7A57Z3IBXBKZU7OFZUGP2O","short_pith_number":"pith:DE7Z7A57","schema_version":"1.0","canonical_sha256":"193f9f83bfced01b8559a7dc5cd0cfd3935f535126743d9abf3cab93ef7c5b46","source":{"kind":"arxiv","id":"1901.08616","version":3},"attestation_state":"computed","paper":{"title":"Boosting Standard Classification Architectures Through a Ranking Regularizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Ahmed Taha, Larry Davis, Teruhisa Misu, Yi-Ting Chen","submitted_at":"2019-01-24T19:19:31Z","abstract_excerpt":"We employ triplet loss as a feature embedding regularizer to boost classification performance. Standard architectures, like ResNet and Inception, are extended to support both losses with minimal hyper-parameter tuning. This promotes generality while fine-tuning pretrained networks. Triplet loss is a powerful surrogate for recently proposed embedding regularizers. Yet, it is avoided due to large batch-size requirement and high computational cost. Through our experiments, we re-assess these assumptions.\n  During inference, our network supports both classification and embedding tasks without any "},"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":"1901.08616","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-24T19:19:31Z","cross_cats_sorted":[],"title_canon_sha256":"86926d52ae0c70628d9eabd6938b86ce3bd879a0b8a3f34914c170f406f14459","abstract_canon_sha256":"2484125dd44773749fbb1b63898fe67e42d7ba85963e0b641d706c57f1f2062d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:56.023191Z","signature_b64":"T7Jg7CWa0//J98i/ySpY+/t64dNaXyB2TuZ08NVqaCVlhHNSPidT58w0EEhOXEbugpO5sE2urI8TDCEfWYTLAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"193f9f83bfced01b8559a7dc5cd0cfd3935f535126743d9abf3cab93ef7c5b46","last_reissued_at":"2026-07-05T00:44:56.022785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:56.022785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Standard Classification Architectures Through a Ranking Regularizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Ahmed Taha, Larry Davis, Teruhisa Misu, Yi-Ting Chen","submitted_at":"2019-01-24T19:19:31Z","abstract_excerpt":"We employ triplet loss as a feature embedding regularizer to boost classification performance. Standard architectures, like ResNet and Inception, are extended to support both losses with minimal hyper-parameter tuning. This promotes generality while fine-tuning pretrained networks. Triplet loss is a powerful surrogate for recently proposed embedding regularizers. Yet, it is avoided due to large batch-size requirement and high computational cost. Through our experiments, we re-assess these assumptions.\n  During inference, our network supports both classification and embedding tasks without any "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08616","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/1901.08616/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":"1901.08616","created_at":"2026-07-05T00:44:56.022842+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08616v3","created_at":"2026-07-05T00:44:56.022842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08616","created_at":"2026-07-05T00:44:56.022842+00:00"},{"alias_kind":"pith_short_12","alias_value":"DE7Z7A57Z3IB","created_at":"2026-07-05T00:44:56.022842+00:00"},{"alias_kind":"pith_short_16","alias_value":"DE7Z7A57Z3IBXBKZ","created_at":"2026-07-05T00:44:56.022842+00:00"},{"alias_kind":"pith_short_8","alias_value":"DE7Z7A57","created_at":"2026-07-05T00:44:56.022842+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/DE7Z7A57Z3IBXBKZU7OFZUGP2O","json":"https://pith.science/pith/DE7Z7A57Z3IBXBKZU7OFZUGP2O.json","graph_json":"https://pith.science/api/pith-number/DE7Z7A57Z3IBXBKZU7OFZUGP2O/graph.json","events_json":"https://pith.science/api/pith-number/DE7Z7A57Z3IBXBKZU7OFZUGP2O/events.json","paper":"https://pith.science/paper/DE7Z7A57"},"agent_actions":{"view_html":"https://pith.science/pith/DE7Z7A57Z3IBXBKZU7OFZUGP2O","download_json":"https://pith.science/pith/DE7Z7A57Z3IBXBKZU7OFZUGP2O.json","view_paper":"https://pith.science/paper/DE7Z7A57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08616&json=true","fetch_graph":"https://pith.science/api/pith-number/DE7Z7A57Z3IBXBKZU7OFZUGP2O/graph.json","fetch_events":"https://pith.science/api/pith-number/DE7Z7A57Z3IBXBKZU7OFZUGP2O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DE7Z7A57Z3IBXBKZU7OFZUGP2O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DE7Z7A57Z3IBXBKZU7OFZUGP2O/action/storage_attestation","attest_author":"https://pith.science/pith/DE7Z7A57Z3IBXBKZU7OFZUGP2O/action/author_attestation","sign_citation":"https://pith.science/pith/DE7Z7A57Z3IBXBKZU7OFZUGP2O/action/citation_signature","submit_replication":"https://pith.science/pith/DE7Z7A57Z3IBXBKZU7OFZUGP2O/action/replication_record"}},"created_at":"2026-07-05T00:44:56.022842+00:00","updated_at":"2026-07-05T00:44:56.022842+00:00"}