{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VMO3VDI43R7LG4ICWH5CFREIHN","short_pith_number":"pith:VMO3VDI4","schema_version":"1.0","canonical_sha256":"ab1dba8d1cdc7eb37102b1fa22c4883b4625c2e3387917fb54faf825dbcf7859","source":{"kind":"arxiv","id":"2201.05887","version":2},"attestation_state":"computed","paper":{"title":"Domain Adaptation via Bidirectional Cross-Attention Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Pengxin Guo, Xiyu Wang, Yu Zhang","submitted_at":"2022-01-15T16:49:56Z","abstract_excerpt":"Domain Adaptation (DA) aims to leverage the knowledge learned from a source domain with ample labeled data to a target domain with unlabeled data only. Most existing studies on DA contribute to learning domain-invariant feature representations for both domains by minimizing the domain gap based on convolution-based neural networks. Recently, vision transformers significantly improved performance in multiple vision tasks. Built on vision transformers, in this paper we propose a Bidirectional Cross-Attention Transformer (BCAT) for DA with the aim to improve the performance. In the proposed BCAT,"},"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":"2201.05887","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-01-15T16:49:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5e0c9cec24760ee603a6eb4afe280c75d15969cc649a1e02736ba86af77c1a0e","abstract_canon_sha256":"ada5232d368acfacf9e59dc2534c86e81164c45c288803e168a9e3f965a8d243"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:40.350676Z","signature_b64":"Cex2sAb1/WjVgTKqSP3FFXeNzfsurdsMobXlXUGcTrBtH6b6uhxiLgzYntGECcKDy3btb8lYdAU+pE67bPDcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab1dba8d1cdc7eb37102b1fa22c4883b4625c2e3387917fb54faf825dbcf7859","last_reissued_at":"2026-07-05T05:02:40.350162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:40.350162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Adaptation via Bidirectional Cross-Attention Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Pengxin Guo, Xiyu Wang, Yu Zhang","submitted_at":"2022-01-15T16:49:56Z","abstract_excerpt":"Domain Adaptation (DA) aims to leverage the knowledge learned from a source domain with ample labeled data to a target domain with unlabeled data only. Most existing studies on DA contribute to learning domain-invariant feature representations for both domains by minimizing the domain gap based on convolution-based neural networks. Recently, vision transformers significantly improved performance in multiple vision tasks. Built on vision transformers, in this paper we propose a Bidirectional Cross-Attention Transformer (BCAT) for DA with the aim to improve the performance. In the proposed BCAT,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05887","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/2201.05887/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":"2201.05887","created_at":"2026-07-05T05:02:40.350231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.05887v2","created_at":"2026-07-05T05:02:40.350231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05887","created_at":"2026-07-05T05:02:40.350231+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMO3VDI43R7L","created_at":"2026-07-05T05:02:40.350231+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMO3VDI43R7LG4IC","created_at":"2026-07-05T05:02:40.350231+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMO3VDI4","created_at":"2026-07-05T05:02:40.350231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04073","citing_title":"TransAdapter: Vision Transformer for Feature-Centric Unsupervised Domain Adaptation","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VMO3VDI43R7LG4ICWH5CFREIHN","json":"https://pith.science/pith/VMO3VDI43R7LG4ICWH5CFREIHN.json","graph_json":"https://pith.science/api/pith-number/VMO3VDI43R7LG4ICWH5CFREIHN/graph.json","events_json":"https://pith.science/api/pith-number/VMO3VDI43R7LG4ICWH5CFREIHN/events.json","paper":"https://pith.science/paper/VMO3VDI4"},"agent_actions":{"view_html":"https://pith.science/pith/VMO3VDI43R7LG4ICWH5CFREIHN","download_json":"https://pith.science/pith/VMO3VDI43R7LG4ICWH5CFREIHN.json","view_paper":"https://pith.science/paper/VMO3VDI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.05887&json=true","fetch_graph":"https://pith.science/api/pith-number/VMO3VDI43R7LG4ICWH5CFREIHN/graph.json","fetch_events":"https://pith.science/api/pith-number/VMO3VDI43R7LG4ICWH5CFREIHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMO3VDI43R7LG4ICWH5CFREIHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMO3VDI43R7LG4ICWH5CFREIHN/action/storage_attestation","attest_author":"https://pith.science/pith/VMO3VDI43R7LG4ICWH5CFREIHN/action/author_attestation","sign_citation":"https://pith.science/pith/VMO3VDI43R7LG4ICWH5CFREIHN/action/citation_signature","submit_replication":"https://pith.science/pith/VMO3VDI43R7LG4ICWH5CFREIHN/action/replication_record"}},"created_at":"2026-07-05T05:02:40.350231+00:00","updated_at":"2026-07-05T05:02:40.350231+00:00"}