{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TGGQWY2CSHP2TWTV2UCODYANJY","short_pith_number":"pith:TGGQWY2C","schema_version":"1.0","canonical_sha256":"998d0b634291dfa9da75d504e1e00d4e1fb73a073a036327b40f528b3e295508","source":{"kind":"arxiv","id":"2110.13266","version":1},"attestation_state":"computed","paper":{"title":"Image Quality Assessment using Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.IV"],"primary_cat":"cs.CV","authors_text":"Alan C. Bovik, Balu Adsumilli, Neil Birkbeck, Pavan C. Madhusudana, Yilin Wang","submitted_at":"2021-10-25T21:01:00Z","abstract_excerpt":"We consider the problem of obtaining image quality representations in a self-supervised manner. We use prediction of distortion type and degree as an auxiliary task to learn features from an unlabeled image dataset containing a mixture of synthetic and realistic distortions. We then train a deep Convolutional Neural Network (CNN) using a contrastive pairwise objective to solve the auxiliary problem. We refer to the proposed training framework and resulting deep IQA model as the CONTRastive Image QUality Evaluator (CONTRIQUE). During evaluation, the CNN weights are frozen and a linear regressor"},"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":"2110.13266","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-25T21:01:00Z","cross_cats_sorted":["cs.MM","eess.IV"],"title_canon_sha256":"aa4cee4a697cb1be66fc880d221881eaecd880cc64c18e996b258f98be201594","abstract_canon_sha256":"94ad2af2da3c1cd87e33825a842facdfc6c8beaef29adc86594aca5fbcdea227"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:57.356138Z","signature_b64":"uxweTipSquOnRu7V7uXGUa+RUhNG7wt2pE0FRYt+oAm3oQ5n4JzZ1GsEBlJgrze4t49Z34RGtsHMlSqfnlm2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"998d0b634291dfa9da75d504e1e00d4e1fb73a073a036327b40f528b3e295508","last_reissued_at":"2026-07-05T04:35:57.355479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:57.355479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Quality Assessment using Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.IV"],"primary_cat":"cs.CV","authors_text":"Alan C. Bovik, Balu Adsumilli, Neil Birkbeck, Pavan C. Madhusudana, Yilin Wang","submitted_at":"2021-10-25T21:01:00Z","abstract_excerpt":"We consider the problem of obtaining image quality representations in a self-supervised manner. We use prediction of distortion type and degree as an auxiliary task to learn features from an unlabeled image dataset containing a mixture of synthetic and realistic distortions. We then train a deep Convolutional Neural Network (CNN) using a contrastive pairwise objective to solve the auxiliary problem. We refer to the proposed training framework and resulting deep IQA model as the CONTRastive Image QUality Evaluator (CONTRIQUE). During evaluation, the CNN weights are frozen and a linear regressor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13266","kind":"arxiv","version":1},"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/2110.13266/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":"2110.13266","created_at":"2026-07-05T04:35:57.355564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.13266v1","created_at":"2026-07-05T04:35:57.355564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13266","created_at":"2026-07-05T04:35:57.355564+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGGQWY2CSHP2","created_at":"2026-07-05T04:35:57.355564+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGGQWY2CSHP2TWTV","created_at":"2026-07-05T04:35:57.355564+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGGQWY2C","created_at":"2026-07-05T04:35:57.355564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20108","citing_title":"EFIQA: Explainable Fundus Image Quality Assessment via Anatomical Priors","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TGGQWY2CSHP2TWTV2UCODYANJY","json":"https://pith.science/pith/TGGQWY2CSHP2TWTV2UCODYANJY.json","graph_json":"https://pith.science/api/pith-number/TGGQWY2CSHP2TWTV2UCODYANJY/graph.json","events_json":"https://pith.science/api/pith-number/TGGQWY2CSHP2TWTV2UCODYANJY/events.json","paper":"https://pith.science/paper/TGGQWY2C"},"agent_actions":{"view_html":"https://pith.science/pith/TGGQWY2CSHP2TWTV2UCODYANJY","download_json":"https://pith.science/pith/TGGQWY2CSHP2TWTV2UCODYANJY.json","view_paper":"https://pith.science/paper/TGGQWY2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.13266&json=true","fetch_graph":"https://pith.science/api/pith-number/TGGQWY2CSHP2TWTV2UCODYANJY/graph.json","fetch_events":"https://pith.science/api/pith-number/TGGQWY2CSHP2TWTV2UCODYANJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGGQWY2CSHP2TWTV2UCODYANJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGGQWY2CSHP2TWTV2UCODYANJY/action/storage_attestation","attest_author":"https://pith.science/pith/TGGQWY2CSHP2TWTV2UCODYANJY/action/author_attestation","sign_citation":"https://pith.science/pith/TGGQWY2CSHP2TWTV2UCODYANJY/action/citation_signature","submit_replication":"https://pith.science/pith/TGGQWY2CSHP2TWTV2UCODYANJY/action/replication_record"}},"created_at":"2026-07-05T04:35:57.355564+00:00","updated_at":"2026-07-05T04:35:57.355564+00:00"}