{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:V4TSD7G4GEMFBETZDZQLLB2KMB","short_pith_number":"pith:V4TSD7G4","schema_version":"1.0","canonical_sha256":"af2721fcdc31185092791e60b5874a605050d68cd52656f93c05eee53b7cc0d1","source":{"kind":"arxiv","id":"2110.14240","version":2},"attestation_state":"computed","paper":{"title":"3rd Place Solution for VisDA 2021 Challenge -- Universally Domain Adaptive Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haojin Liao, Pengfei Xu, Qiang Wang, Shanghang Zhang, Sicheng Zhao, Tengfei Xing, Xiangyu Yue, Xiaolin Song, Xingxu Yao, Yueming Zhang","submitted_at":"2021-10-27T07:48:29Z","abstract_excerpt":"The Visual Domain Adaptation (VisDA) 2021 Challenge calls for unsupervised domain adaptation (UDA) methods that can deal with both input distribution shift and label set variance between the source and target domains. In this report, we introduce a universal domain adaptation (UniDA) method by aggregating several popular feature extraction and domain adaptation schemes. First, we utilize VOLO, a Transformer-based architecture with state-of-the-art performance in several visual tasks, as the backbone to extract effective feature representations. Second, we modify the open-set classifier of OVAN"},"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":"2110.14240","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-27T07:48:29Z","cross_cats_sorted":[],"title_canon_sha256":"216e558af8a90e6aa8726eeec698c6f601daa475942d9e58101c3ddebe3cae90","abstract_canon_sha256":"7c6f744c32025a097d990c33a093b61f9450820a18a7a41208fffd529b1fcf0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:01.742630Z","signature_b64":"pJESF678yTVe3E+CY/OTxwsaz6Q0l7A9GFyBcWcy3JnJX+RkjGmZcRxos318QEMLUDve2W8+hDMmOFYB9TSmAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af2721fcdc31185092791e60b5874a605050d68cd52656f93c05eee53b7cc0d1","last_reissued_at":"2026-07-05T10:21:01.742135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:01.742135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3rd Place Solution for VisDA 2021 Challenge -- Universally Domain Adaptive Image Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haojin Liao, Pengfei Xu, Qiang Wang, Shanghang Zhang, Sicheng Zhao, Tengfei Xing, Xiangyu Yue, Xiaolin Song, Xingxu Yao, Yueming Zhang","submitted_at":"2021-10-27T07:48:29Z","abstract_excerpt":"The Visual Domain Adaptation (VisDA) 2021 Challenge calls for unsupervised domain adaptation (UDA) methods that can deal with both input distribution shift and label set variance between the source and target domains. In this report, we introduce a universal domain adaptation (UniDA) method by aggregating several popular feature extraction and domain adaptation schemes. First, we utilize VOLO, a Transformer-based architecture with state-of-the-art performance in several visual tasks, as the backbone to extract effective feature representations. Second, we modify the open-set classifier of OVAN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14240","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/2110.14240/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":"2110.14240","created_at":"2026-07-05T10:21:01.742193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.14240v2","created_at":"2026-07-05T10:21:01.742193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14240","created_at":"2026-07-05T10:21:01.742193+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4TSD7G4GEMF","created_at":"2026-07-05T10:21:01.742193+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4TSD7G4GEMFBETZ","created_at":"2026-07-05T10:21:01.742193+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4TSD7G4","created_at":"2026-07-05T10:21:01.742193+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/V4TSD7G4GEMFBETZDZQLLB2KMB","json":"https://pith.science/pith/V4TSD7G4GEMFBETZDZQLLB2KMB.json","graph_json":"https://pith.science/api/pith-number/V4TSD7G4GEMFBETZDZQLLB2KMB/graph.json","events_json":"https://pith.science/api/pith-number/V4TSD7G4GEMFBETZDZQLLB2KMB/events.json","paper":"https://pith.science/paper/V4TSD7G4"},"agent_actions":{"view_html":"https://pith.science/pith/V4TSD7G4GEMFBETZDZQLLB2KMB","download_json":"https://pith.science/pith/V4TSD7G4GEMFBETZDZQLLB2KMB.json","view_paper":"https://pith.science/paper/V4TSD7G4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.14240&json=true","fetch_graph":"https://pith.science/api/pith-number/V4TSD7G4GEMFBETZDZQLLB2KMB/graph.json","fetch_events":"https://pith.science/api/pith-number/V4TSD7G4GEMFBETZDZQLLB2KMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4TSD7G4GEMFBETZDZQLLB2KMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4TSD7G4GEMFBETZDZQLLB2KMB/action/storage_attestation","attest_author":"https://pith.science/pith/V4TSD7G4GEMFBETZDZQLLB2KMB/action/author_attestation","sign_citation":"https://pith.science/pith/V4TSD7G4GEMFBETZDZQLLB2KMB/action/citation_signature","submit_replication":"https://pith.science/pith/V4TSD7G4GEMFBETZDZQLLB2KMB/action/replication_record"}},"created_at":"2026-07-05T10:21:01.742193+00:00","updated_at":"2026-07-05T10:21:01.742193+00:00"}