{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RFCFDWONN6Z56SKC63D2SPRRGG","short_pith_number":"pith:RFCFDWON","schema_version":"1.0","canonical_sha256":"894451d9cd6fb3df4942f6c7a93e31319d9566303da1bc73fc46c129a9d4559f","source":{"kind":"arxiv","id":"2111.12940","version":2},"attestation_state":"computed","paper":{"title":"Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Binhui Xie, Chi Harold Liu, Longhui Yuan, Shuang Li, Xinjing Cheng","submitted_at":"2021-11-25T06:40:58Z","abstract_excerpt":"Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo labels are typically biased to the majority classes and basically noisy, leading to an error-prone and suboptimal model. In this paper, we propose a simple region-based active learning approach for semantic segmentation under a domain shift, aiming to automatically query a small partition of image regions to be labeled while maximizing segmentation performa"},"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":"2111.12940","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T06:40:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"056176051ee5e7d509dadc876b222107e43bd8abdbff34b63b5ea549f819d689","abstract_canon_sha256":"8fe9bdc3a5ad6fdb5f2ade7e7db058681a43bc43b1777246d86f6900036e2137"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:59.881062Z","signature_b64":"evgcmj7YUu1XNmrrf6ZtI9UQ1Fn4fpSQ+NwIUcRJVn4zV5/jY146Wk/Jz28iad7V980muaiL7jKt7N6hlAdNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"894451d9cd6fb3df4942f6c7a93e31319d9566303da1bc73fc46c129a9d4559f","last_reissued_at":"2026-07-05T04:08:59.880532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:59.880532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Binhui Xie, Chi Harold Liu, Longhui Yuan, Shuang Li, Xinjing Cheng","submitted_at":"2021-11-25T06:40:58Z","abstract_excerpt":"Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network. However, realistic segmentation datasets are highly imbalanced, pseudo labels are typically biased to the majority classes and basically noisy, leading to an error-prone and suboptimal model. In this paper, we propose a simple region-based active learning approach for semantic segmentation under a domain shift, aiming to automatically query a small partition of image regions to be labeled while maximizing segmentation performa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12940","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/2111.12940/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":"2111.12940","created_at":"2026-07-05T04:08:59.880605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.12940v2","created_at":"2026-07-05T04:08:59.880605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12940","created_at":"2026-07-05T04:08:59.880605+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFCFDWONN6Z5","created_at":"2026-07-05T04:08:59.880605+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFCFDWONN6Z56SKC","created_at":"2026-07-05T04:08:59.880605+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFCFDWON","created_at":"2026-07-05T04:08:59.880605+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/RFCFDWONN6Z56SKC63D2SPRRGG","json":"https://pith.science/pith/RFCFDWONN6Z56SKC63D2SPRRGG.json","graph_json":"https://pith.science/api/pith-number/RFCFDWONN6Z56SKC63D2SPRRGG/graph.json","events_json":"https://pith.science/api/pith-number/RFCFDWONN6Z56SKC63D2SPRRGG/events.json","paper":"https://pith.science/paper/RFCFDWON"},"agent_actions":{"view_html":"https://pith.science/pith/RFCFDWONN6Z56SKC63D2SPRRGG","download_json":"https://pith.science/pith/RFCFDWONN6Z56SKC63D2SPRRGG.json","view_paper":"https://pith.science/paper/RFCFDWON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.12940&json=true","fetch_graph":"https://pith.science/api/pith-number/RFCFDWONN6Z56SKC63D2SPRRGG/graph.json","fetch_events":"https://pith.science/api/pith-number/RFCFDWONN6Z56SKC63D2SPRRGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFCFDWONN6Z56SKC63D2SPRRGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFCFDWONN6Z56SKC63D2SPRRGG/action/storage_attestation","attest_author":"https://pith.science/pith/RFCFDWONN6Z56SKC63D2SPRRGG/action/author_attestation","sign_citation":"https://pith.science/pith/RFCFDWONN6Z56SKC63D2SPRRGG/action/citation_signature","submit_replication":"https://pith.science/pith/RFCFDWONN6Z56SKC63D2SPRRGG/action/replication_record"}},"created_at":"2026-07-05T04:08:59.880605+00:00","updated_at":"2026-07-05T04:08:59.880605+00:00"}