{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SQ2LAXZ2MWJM3DWIAMWBBTK7HX","short_pith_number":"pith:SQ2LAXZ2","schema_version":"1.0","canonical_sha256":"9434b05f3a6592cd8ec8032c10cd5f3df836003674725459cb33cd8671491ce1","source":{"kind":"arxiv","id":"2208.14227","version":2},"attestation_state":"computed","paper":{"title":"CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anuraag Bhattacharya, Jaswin Kasi, Midhun Vayyat, Rahul Tallamraju, Shuaib Ahmed","submitted_at":"2022-08-27T05:13:14Z","abstract_excerpt":"In this work, we propose CLUDA, a simple, yet novel method for performing unsupervised domain adaptation (UDA) for semantic segmentation by incorporating contrastive losses into a student-teacher learning paradigm, that makes use of pseudo-labels generated from the target domain by the teacher network. More specifically, we extract a multi-level fused-feature map from the encoder, and apply contrastive loss across different classes and different domains, via source-target mixing of images. We consistently improve performance on various feature encoder architectures and for different domain ada"},"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":"2208.14227","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-27T05:13:14Z","cross_cats_sorted":[],"title_canon_sha256":"1d7c3c56eb8e7b59c1a89d356866cc69980931010e1d6cb4800e3daed8964e16","abstract_canon_sha256":"d66aca698aebf8239124a5eccdd8aca19ac54d213cdde93a819eb81060b1d255"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:57.061687Z","signature_b64":"8ja9qDo41Kg9aXyTwjyatWRvGikf1IbTWf1aU9NsuhT6hZcfnRd+PbdZHKYzIg9wMc4Bx2CHwXUi3y5c3hj4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9434b05f3a6592cd8ec8032c10cd5f3df836003674725459cb33cd8671491ce1","last_reissued_at":"2026-07-05T05:13:57.061207Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:57.061207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anuraag Bhattacharya, Jaswin Kasi, Midhun Vayyat, Rahul Tallamraju, Shuaib Ahmed","submitted_at":"2022-08-27T05:13:14Z","abstract_excerpt":"In this work, we propose CLUDA, a simple, yet novel method for performing unsupervised domain adaptation (UDA) for semantic segmentation by incorporating contrastive losses into a student-teacher learning paradigm, that makes use of pseudo-labels generated from the target domain by the teacher network. More specifically, we extract a multi-level fused-feature map from the encoder, and apply contrastive loss across different classes and different domains, via source-target mixing of images. We consistently improve performance on various feature encoder architectures and for different domain ada"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14227","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/2208.14227/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":"2208.14227","created_at":"2026-07-05T05:13:57.061263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.14227v2","created_at":"2026-07-05T05:13:57.061263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14227","created_at":"2026-07-05T05:13:57.061263+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQ2LAXZ2MWJM","created_at":"2026-07-05T05:13:57.061263+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQ2LAXZ2MWJM3DWI","created_at":"2026-07-05T05:13:57.061263+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQ2LAXZ2","created_at":"2026-07-05T05:13:57.061263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09040","citing_title":"Pseudolabel guided pixels contrast for domain adaptive semantic segmentation","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQ2LAXZ2MWJM3DWIAMWBBTK7HX","json":"https://pith.science/pith/SQ2LAXZ2MWJM3DWIAMWBBTK7HX.json","graph_json":"https://pith.science/api/pith-number/SQ2LAXZ2MWJM3DWIAMWBBTK7HX/graph.json","events_json":"https://pith.science/api/pith-number/SQ2LAXZ2MWJM3DWIAMWBBTK7HX/events.json","paper":"https://pith.science/paper/SQ2LAXZ2"},"agent_actions":{"view_html":"https://pith.science/pith/SQ2LAXZ2MWJM3DWIAMWBBTK7HX","download_json":"https://pith.science/pith/SQ2LAXZ2MWJM3DWIAMWBBTK7HX.json","view_paper":"https://pith.science/paper/SQ2LAXZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.14227&json=true","fetch_graph":"https://pith.science/api/pith-number/SQ2LAXZ2MWJM3DWIAMWBBTK7HX/graph.json","fetch_events":"https://pith.science/api/pith-number/SQ2LAXZ2MWJM3DWIAMWBBTK7HX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQ2LAXZ2MWJM3DWIAMWBBTK7HX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQ2LAXZ2MWJM3DWIAMWBBTK7HX/action/storage_attestation","attest_author":"https://pith.science/pith/SQ2LAXZ2MWJM3DWIAMWBBTK7HX/action/author_attestation","sign_citation":"https://pith.science/pith/SQ2LAXZ2MWJM3DWIAMWBBTK7HX/action/citation_signature","submit_replication":"https://pith.science/pith/SQ2LAXZ2MWJM3DWIAMWBBTK7HX/action/replication_record"}},"created_at":"2026-07-05T05:13:57.061263+00:00","updated_at":"2026-07-05T05:13:57.061263+00:00"}