{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Z7LHKJKKBKUUYDU5FPTJNLR2U5","short_pith_number":"pith:Z7LHKJKK","schema_version":"1.0","canonical_sha256":"cfd675254a0aa94c0e9d2be696ae3aa75e214de648820aa5c77a4973e7b0c58c","source":{"kind":"arxiv","id":"2108.08012","version":1},"attestation_state":"computed","paper":{"title":"Multi-Anchor Active Domain Adaptation for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Bian, Chenglang Yuan, Donghuan Lu, Dong Wei, Kai Ma, Munan Ning, Shuang Yu, Yefeng Zheng","submitted_at":"2021-08-18T07:33:13Z","abstract_excerpt":"Unsupervised domain adaption has proven to be an effective approach for alleviating the intensive workload of manual annotation by aligning the synthetic source-domain data and the real-world target-domain samples. Unfortunately, mapping the target-domain distribution to the source-domain unconditionally may distort the essential structural information of the target-domain data. To this end, we firstly propose to introduce a novel multi-anchor based active learning strategy to assist domain adaptation regarding the semantic segmentation task. By innovatively adopting multiple anchors instead o"},"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":"2108.08012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-18T07:33:13Z","cross_cats_sorted":[],"title_canon_sha256":"0f5d856fd7d375caec20cc51e316138d1631f090d91f96c3cf722c46648f7178","abstract_canon_sha256":"1b2168c1d77a3d0154bb89c2f20b0fda602e3339c432dee17bf530301a9dfc04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:50.740228Z","signature_b64":"k9cxQ8vDdiwt+nKpvsoIWqHea0kKfwXfY86KVtjUGofoFZKoWO3xHp2ffrsuIv8BxOepynbyWadhDV1DlD86BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfd675254a0aa94c0e9d2be696ae3aa75e214de648820aa5c77a4973e7b0c58c","last_reissued_at":"2026-07-05T03:06:50.739819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:50.739819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Anchor Active Domain Adaptation for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Bian, Chenglang Yuan, Donghuan Lu, Dong Wei, Kai Ma, Munan Ning, Shuang Yu, Yefeng Zheng","submitted_at":"2021-08-18T07:33:13Z","abstract_excerpt":"Unsupervised domain adaption has proven to be an effective approach for alleviating the intensive workload of manual annotation by aligning the synthetic source-domain data and the real-world target-domain samples. Unfortunately, mapping the target-domain distribution to the source-domain unconditionally may distort the essential structural information of the target-domain data. To this end, we firstly propose to introduce a novel multi-anchor based active learning strategy to assist domain adaptation regarding the semantic segmentation task. By innovatively adopting multiple anchors instead o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08012","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/2108.08012/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":"2108.08012","created_at":"2026-07-05T03:06:50.739879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.08012v1","created_at":"2026-07-05T03:06:50.739879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08012","created_at":"2026-07-05T03:06:50.739879+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7LHKJKKBKUU","created_at":"2026-07-05T03:06:50.739879+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7LHKJKKBKUUYDU5","created_at":"2026-07-05T03:06:50.739879+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7LHKJKK","created_at":"2026-07-05T03:06:50.739879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.13214","citing_title":"Wavelet-based Variational Autoencoders for High-Resolution Image Generation","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7LHKJKKBKUUYDU5FPTJNLR2U5","json":"https://pith.science/pith/Z7LHKJKKBKUUYDU5FPTJNLR2U5.json","graph_json":"https://pith.science/api/pith-number/Z7LHKJKKBKUUYDU5FPTJNLR2U5/graph.json","events_json":"https://pith.science/api/pith-number/Z7LHKJKKBKUUYDU5FPTJNLR2U5/events.json","paper":"https://pith.science/paper/Z7LHKJKK"},"agent_actions":{"view_html":"https://pith.science/pith/Z7LHKJKKBKUUYDU5FPTJNLR2U5","download_json":"https://pith.science/pith/Z7LHKJKKBKUUYDU5FPTJNLR2U5.json","view_paper":"https://pith.science/paper/Z7LHKJKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.08012&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7LHKJKKBKUUYDU5FPTJNLR2U5/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7LHKJKKBKUUYDU5FPTJNLR2U5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7LHKJKKBKUUYDU5FPTJNLR2U5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7LHKJKKBKUUYDU5FPTJNLR2U5/action/storage_attestation","attest_author":"https://pith.science/pith/Z7LHKJKKBKUUYDU5FPTJNLR2U5/action/author_attestation","sign_citation":"https://pith.science/pith/Z7LHKJKKBKUUYDU5FPTJNLR2U5/action/citation_signature","submit_replication":"https://pith.science/pith/Z7LHKJKKBKUUYDU5FPTJNLR2U5/action/replication_record"}},"created_at":"2026-07-05T03:06:50.739879+00:00","updated_at":"2026-07-05T03:06:50.739879+00:00"}