{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:V7XSEE4ITB6ANG4ZXFVSAHD4RE","short_pith_number":"pith:V7XSEE4I","schema_version":"1.0","canonical_sha256":"afef221388987c069b99b96b201c7c8905f3fa0dac3ded73a29c6ae56ce04d85","source":{"kind":"arxiv","id":"2112.10453","version":2},"attestation_state":"computed","paper":{"title":"Learning with Label Noise for Image Retrieval by Selecting Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnaud Sors, Rafael Sampaio de Rezende, Sarah Ibrahimi, St\\'ephane Clinchant","submitted_at":"2021-12-20T11:27:48Z","abstract_excerpt":"Learning with noisy labels is an active research area for image classification. However, the effect of noisy labels on image retrieval has been less studied. In this work, we propose a noise-resistant method for image retrieval named Teacher-based Selection of Interactions, T-SINT, which identifies noisy interactions, ie. elements in the distance matrix, and selects correct positive and negative interactions to be considered in the retrieval loss by using a teacher-based training setup which contributes to the stability. As a result, it consistently outperforms state-of-the-art methods on high"},"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":"2112.10453","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-20T11:27:48Z","cross_cats_sorted":[],"title_canon_sha256":"4f853c39cd869509f00965b6593f509037daf5ad1491c4c31ed084035eb80830","abstract_canon_sha256":"c7c6b977e8945d8f693dbd71a18f9a09760680d0dd7baa2f73fb3447f254abe8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:42:25.788551Z","signature_b64":"hQTQam2b/nbUly+ChagTa7402guGOD2imrGTgSVDXl2aqulYjqm8YetAp5QUN+cgdvcJNHvyMG6E7yl91WINAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afef221388987c069b99b96b201c7c8905f3fa0dac3ded73a29c6ae56ce04d85","last_reissued_at":"2026-07-05T03:42:25.788104Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:42:25.788104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning with Label Noise for Image Retrieval by Selecting Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnaud Sors, Rafael Sampaio de Rezende, Sarah Ibrahimi, St\\'ephane Clinchant","submitted_at":"2021-12-20T11:27:48Z","abstract_excerpt":"Learning with noisy labels is an active research area for image classification. However, the effect of noisy labels on image retrieval has been less studied. In this work, we propose a noise-resistant method for image retrieval named Teacher-based Selection of Interactions, T-SINT, which identifies noisy interactions, ie. elements in the distance matrix, and selects correct positive and negative interactions to be considered in the retrieval loss by using a teacher-based training setup which contributes to the stability. As a result, it consistently outperforms state-of-the-art methods on high"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.10453","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.10453/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":"2112.10453","created_at":"2026-07-05T03:42:25.788162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.10453v2","created_at":"2026-07-05T03:42:25.788162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.10453","created_at":"2026-07-05T03:42:25.788162+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7XSEE4ITB6A","created_at":"2026-07-05T03:42:25.788162+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7XSEE4ITB6ANG4Z","created_at":"2026-07-05T03:42:25.788162+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7XSEE4I","created_at":"2026-07-05T03:42:25.788162+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/V7XSEE4ITB6ANG4ZXFVSAHD4RE","json":"https://pith.science/pith/V7XSEE4ITB6ANG4ZXFVSAHD4RE.json","graph_json":"https://pith.science/api/pith-number/V7XSEE4ITB6ANG4ZXFVSAHD4RE/graph.json","events_json":"https://pith.science/api/pith-number/V7XSEE4ITB6ANG4ZXFVSAHD4RE/events.json","paper":"https://pith.science/paper/V7XSEE4I"},"agent_actions":{"view_html":"https://pith.science/pith/V7XSEE4ITB6ANG4ZXFVSAHD4RE","download_json":"https://pith.science/pith/V7XSEE4ITB6ANG4ZXFVSAHD4RE.json","view_paper":"https://pith.science/paper/V7XSEE4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.10453&json=true","fetch_graph":"https://pith.science/api/pith-number/V7XSEE4ITB6ANG4ZXFVSAHD4RE/graph.json","fetch_events":"https://pith.science/api/pith-number/V7XSEE4ITB6ANG4ZXFVSAHD4RE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7XSEE4ITB6ANG4ZXFVSAHD4RE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7XSEE4ITB6ANG4ZXFVSAHD4RE/action/storage_attestation","attest_author":"https://pith.science/pith/V7XSEE4ITB6ANG4ZXFVSAHD4RE/action/author_attestation","sign_citation":"https://pith.science/pith/V7XSEE4ITB6ANG4ZXFVSAHD4RE/action/citation_signature","submit_replication":"https://pith.science/pith/V7XSEE4ITB6ANG4ZXFVSAHD4RE/action/replication_record"}},"created_at":"2026-07-05T03:42:25.788162+00:00","updated_at":"2026-07-05T03:42:25.788162+00:00"}