{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OVHC7QSFJ6S4ITA5ANG3GPMFYX","short_pith_number":"pith:OVHC7QSF","schema_version":"1.0","canonical_sha256":"754e2fc2454fa5c44c1d034db33d85c5e2024250059654c9d38f2c1ebeda7630","source":{"kind":"arxiv","id":"2210.01578","version":1},"attestation_state":"computed","paper":{"title":"Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Hongtao Lu, St\\'ephane Lathuili\\`ere, Subhankar Roy, Yangsong Zhang","submitted_at":"2022-10-04T13:03:17Z","abstract_excerpt":"In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data distributions. To address MTDA, we propose a self-training strategy that employs pseudo-labels to induce cooperation among multiple domain-specific classifiers. We employ feature stylization as an efficient way to generate image views that forms an integral part of self-training. Additionally, to prevent the network from overfitting to noisy pseudo-labels, w"},"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":"2210.01578","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-04T13:03:17Z","cross_cats_sorted":[],"title_canon_sha256":"55051cdfbb108ad16402e7e2ed314ab81d9a13431e558f163c1bafe9bd9a652c","abstract_canon_sha256":"91ee9402a66c23f30b67d5493794f50e17cdce8d06b7d437495a0773d9081d33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:12.282972Z","signature_b64":"8zP1bwskV4OoFbSXEwblD6feRF06HLrxTxScSxNvqpJ1IQCmjD0OFabBK0xW6u1pY9wMs0hUl3rN0gsbvXyXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"754e2fc2454fa5c44c1d034db33d85c5e2024250059654c9d38f2c1ebeda7630","last_reissued_at":"2026-07-05T05:03:12.282548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:12.282548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elisa Ricci, Hongtao Lu, St\\'ephane Lathuili\\`ere, Subhankar Roy, Yangsong Zhang","submitted_at":"2022-10-04T13:03:17Z","abstract_excerpt":"In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data distributions. To address MTDA, we propose a self-training strategy that employs pseudo-labels to induce cooperation among multiple domain-specific classifiers. We employ feature stylization as an efficient way to generate image views that forms an integral part of self-training. Additionally, to prevent the network from overfitting to noisy pseudo-labels, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01578","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/2210.01578/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":"2210.01578","created_at":"2026-07-05T05:03:12.282612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.01578v1","created_at":"2026-07-05T05:03:12.282612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01578","created_at":"2026-07-05T05:03:12.282612+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVHC7QSFJ6S4","created_at":"2026-07-05T05:03:12.282612+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVHC7QSFJ6S4ITA5","created_at":"2026-07-05T05:03:12.282612+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVHC7QSF","created_at":"2026-07-05T05:03:12.282612+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/OVHC7QSFJ6S4ITA5ANG3GPMFYX","json":"https://pith.science/pith/OVHC7QSFJ6S4ITA5ANG3GPMFYX.json","graph_json":"https://pith.science/api/pith-number/OVHC7QSFJ6S4ITA5ANG3GPMFYX/graph.json","events_json":"https://pith.science/api/pith-number/OVHC7QSFJ6S4ITA5ANG3GPMFYX/events.json","paper":"https://pith.science/paper/OVHC7QSF"},"agent_actions":{"view_html":"https://pith.science/pith/OVHC7QSFJ6S4ITA5ANG3GPMFYX","download_json":"https://pith.science/pith/OVHC7QSFJ6S4ITA5ANG3GPMFYX.json","view_paper":"https://pith.science/paper/OVHC7QSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.01578&json=true","fetch_graph":"https://pith.science/api/pith-number/OVHC7QSFJ6S4ITA5ANG3GPMFYX/graph.json","fetch_events":"https://pith.science/api/pith-number/OVHC7QSFJ6S4ITA5ANG3GPMFYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVHC7QSFJ6S4ITA5ANG3GPMFYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVHC7QSFJ6S4ITA5ANG3GPMFYX/action/storage_attestation","attest_author":"https://pith.science/pith/OVHC7QSFJ6S4ITA5ANG3GPMFYX/action/author_attestation","sign_citation":"https://pith.science/pith/OVHC7QSFJ6S4ITA5ANG3GPMFYX/action/citation_signature","submit_replication":"https://pith.science/pith/OVHC7QSFJ6S4ITA5ANG3GPMFYX/action/replication_record"}},"created_at":"2026-07-05T05:03:12.282612+00:00","updated_at":"2026-07-05T05:03:12.282612+00:00"}