{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XVBEC43ZZVP4XUGRWVHXBVBRND","short_pith_number":"pith:XVBEC43Z","schema_version":"1.0","canonical_sha256":"bd42417379cd5fcbd0d1b54f70d43168f08da270da748d1a9001160be3ff73d4","source":{"kind":"arxiv","id":"2106.04990","version":2},"attestation_state":"computed","paper":{"title":"It Takes Two to Tango: Mixup for Deep Metric Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bill Psomas, Ewa Kijak, Konstantinos Karantzalos, Laurent Amsaleg, Shashanka Venkataramanan, Yannis Avrithis","submitted_at":"2021-06-09T11:20:03Z","abstract_excerpt":"Metric learning involves learning a discriminative representation such that embeddings of similar classes are encouraged to be close, while embeddings of dissimilar classes are pushed far apart. State-of-the-art methods focus mostly on sophisticated loss functions or mining strategies. On the one hand, metric learning losses consider two or more examples at a time. On the other hand, modern data augmentation methods for classification consider two or more examples at a time. The combination of the two ideas is under-studied.\n  In this work, we aim to bridge this gap and improve representations"},"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":"2106.04990","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-09T11:20:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a8753dbba37d1817789ab067e32dfcae3bc67f4d0e4f02044afb557fc8603c70","abstract_canon_sha256":"c3432e8d890f8550129eee4a2cc8e891797bc4dcdfdb7b1fce6ceadbda7bc265"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:15.154821Z","signature_b64":"anSuh3ulrS4OfjUS+f6Hgle8Al2k5F3boMXgblYirvQ3HR2+/xle1soEfheVyUQtiXMTvcXDdSA8RlVBPtREDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd42417379cd5fcbd0d1b54f70d43168f08da270da748d1a9001160be3ff73d4","last_reissued_at":"2026-07-05T04:00:15.154409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:15.154409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"It Takes Two to Tango: Mixup for Deep Metric Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bill Psomas, Ewa Kijak, Konstantinos Karantzalos, Laurent Amsaleg, Shashanka Venkataramanan, Yannis Avrithis","submitted_at":"2021-06-09T11:20:03Z","abstract_excerpt":"Metric learning involves learning a discriminative representation such that embeddings of similar classes are encouraged to be close, while embeddings of dissimilar classes are pushed far apart. State-of-the-art methods focus mostly on sophisticated loss functions or mining strategies. On the one hand, metric learning losses consider two or more examples at a time. On the other hand, modern data augmentation methods for classification consider two or more examples at a time. The combination of the two ideas is under-studied.\n  In this work, we aim to bridge this gap and improve representations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04990","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/2106.04990/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":"2106.04990","created_at":"2026-07-05T04:00:15.154469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.04990v2","created_at":"2026-07-05T04:00:15.154469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04990","created_at":"2026-07-05T04:00:15.154469+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVBEC43ZZVP4","created_at":"2026-07-05T04:00:15.154469+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVBEC43ZZVP4XUGR","created_at":"2026-07-05T04:00:15.154469+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVBEC43Z","created_at":"2026-07-05T04:00:15.154469+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/XVBEC43ZZVP4XUGRWVHXBVBRND","json":"https://pith.science/pith/XVBEC43ZZVP4XUGRWVHXBVBRND.json","graph_json":"https://pith.science/api/pith-number/XVBEC43ZZVP4XUGRWVHXBVBRND/graph.json","events_json":"https://pith.science/api/pith-number/XVBEC43ZZVP4XUGRWVHXBVBRND/events.json","paper":"https://pith.science/paper/XVBEC43Z"},"agent_actions":{"view_html":"https://pith.science/pith/XVBEC43ZZVP4XUGRWVHXBVBRND","download_json":"https://pith.science/pith/XVBEC43ZZVP4XUGRWVHXBVBRND.json","view_paper":"https://pith.science/paper/XVBEC43Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.04990&json=true","fetch_graph":"https://pith.science/api/pith-number/XVBEC43ZZVP4XUGRWVHXBVBRND/graph.json","fetch_events":"https://pith.science/api/pith-number/XVBEC43ZZVP4XUGRWVHXBVBRND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVBEC43ZZVP4XUGRWVHXBVBRND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVBEC43ZZVP4XUGRWVHXBVBRND/action/storage_attestation","attest_author":"https://pith.science/pith/XVBEC43ZZVP4XUGRWVHXBVBRND/action/author_attestation","sign_citation":"https://pith.science/pith/XVBEC43ZZVP4XUGRWVHXBVBRND/action/citation_signature","submit_replication":"https://pith.science/pith/XVBEC43ZZVP4XUGRWVHXBVBRND/action/replication_record"}},"created_at":"2026-07-05T04:00:15.154469+00:00","updated_at":"2026-07-05T04:00:15.154469+00:00"}