{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:PIVJWWW7BALKVA2WQJANFJRNTI","short_pith_number":"pith:PIVJWWW7","schema_version":"1.0","canonical_sha256":"7a2a9b5adf0816aa83568240d2a62d9a2d009542ee044c2b8c29f31ad142c422","source":{"kind":"arxiv","id":"1610.07940","version":2},"attestation_state":"computed","paper":{"title":"End-to-end Learning of Deep Visual Representations for Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Gordo, Diane Larlus, Jerome Revaud, Jon Almazan","submitted_at":"2016-10-25T16:02:42Z","abstract_excerpt":"While deep learning has become a key ingredient in the top performing methods for many computer vision tasks, it has failed so far to bring similar improvements to instance-level image retrieval. In this article, we argue that reasons for the underwhelming results of deep methods on image retrieval are threefold: i) noisy training data, ii) inappropriate deep architecture, and iii) suboptimal training procedure. We address all three issues.\n  First, we leverage a large-scale but noisy landmark dataset and develop an automatic cleaning method that produces a suitable training set for deep retri"},"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":"1610.07940","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-10-25T16:02:42Z","cross_cats_sorted":[],"title_canon_sha256":"f427d993ccef4c7459c86607d6906a9d7dc5138b1e54e9f9858ba3781831fed6","abstract_canon_sha256":"0429603226d79c7f50d7b5523ef633fedf71341c332f8914e9000780a0c0962f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:01.453529Z","signature_b64":"t3Guyni6qnuI04U6ad3nnQLY3Eop4mcgy2b9u1MpGv39dVsNzeMnIvp1zXntLbDMseRTNMfsCF8WKbgsNozMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a2a9b5adf0816aa83568240d2a62d9a2d009542ee044c2b8c29f31ad142c422","last_reissued_at":"2026-05-18T00:45:01.453063Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:01.453063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end Learning of Deep Visual Representations for Image Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Gordo, Diane Larlus, Jerome Revaud, Jon Almazan","submitted_at":"2016-10-25T16:02:42Z","abstract_excerpt":"While deep learning has become a key ingredient in the top performing methods for many computer vision tasks, it has failed so far to bring similar improvements to instance-level image retrieval. In this article, we argue that reasons for the underwhelming results of deep methods on image retrieval are threefold: i) noisy training data, ii) inappropriate deep architecture, and iii) suboptimal training procedure. We address all three issues.\n  First, we leverage a large-scale but noisy landmark dataset and develop an automatic cleaning method that produces a suitable training set for deep retri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.07940","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":"1610.07940","created_at":"2026-05-18T00:45:01.453143+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.07940v2","created_at":"2026-05-18T00:45:01.453143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.07940","created_at":"2026-05-18T00:45:01.453143+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIVJWWW7BALK","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIVJWWW7BALKVA2W","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIVJWWW7","created_at":"2026-05-18T12:30:39.010887+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/PIVJWWW7BALKVA2WQJANFJRNTI","json":"https://pith.science/pith/PIVJWWW7BALKVA2WQJANFJRNTI.json","graph_json":"https://pith.science/api/pith-number/PIVJWWW7BALKVA2WQJANFJRNTI/graph.json","events_json":"https://pith.science/api/pith-number/PIVJWWW7BALKVA2WQJANFJRNTI/events.json","paper":"https://pith.science/paper/PIVJWWW7"},"agent_actions":{"view_html":"https://pith.science/pith/PIVJWWW7BALKVA2WQJANFJRNTI","download_json":"https://pith.science/pith/PIVJWWW7BALKVA2WQJANFJRNTI.json","view_paper":"https://pith.science/paper/PIVJWWW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.07940&json=true","fetch_graph":"https://pith.science/api/pith-number/PIVJWWW7BALKVA2WQJANFJRNTI/graph.json","fetch_events":"https://pith.science/api/pith-number/PIVJWWW7BALKVA2WQJANFJRNTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIVJWWW7BALKVA2WQJANFJRNTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIVJWWW7BALKVA2WQJANFJRNTI/action/storage_attestation","attest_author":"https://pith.science/pith/PIVJWWW7BALKVA2WQJANFJRNTI/action/author_attestation","sign_citation":"https://pith.science/pith/PIVJWWW7BALKVA2WQJANFJRNTI/action/citation_signature","submit_replication":"https://pith.science/pith/PIVJWWW7BALKVA2WQJANFJRNTI/action/replication_record"}},"created_at":"2026-05-18T00:45:01.453143+00:00","updated_at":"2026-05-18T00:45:01.453143+00:00"}