{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DMD7KCBGQDWW7T6DGI7ZI3RBKN","short_pith_number":"pith:DMD7KCBG","schema_version":"1.0","canonical_sha256":"1b07f5082680ed6fcfc3323f946e2153574a7d18f0ebc5f76eeba886127ef936","source":{"kind":"arxiv","id":"1809.00903","version":2},"attestation_state":"computed","paper":{"title":"Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ceyuan Yang, Dahua Lin, Hui Zhou, Jianping Shi, Xinge Zhu","submitted_at":"2018-09-04T11:50:09Z","abstract_excerpt":"Due to the expensive and time-consuming annotations (e.g., segmentation) for real-world images, recent works in computer vision resort to synthetic data. However, the performance on the real image often drops significantly because of the domain shift between the synthetic data and the real images. In this setting, domain adaptation brings an appealing option. The effective approaches of domain adaptation shape the representations that (1) are discriminative for the main task and (2) have good generalization capability for domain shift. To this end, we propose a novel loss function, i.e., Conse"},"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":"1809.00903","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-09-04T11:50:09Z","cross_cats_sorted":[],"title_canon_sha256":"77ddcc6819fd3e7b34c4daddda25ad6e96aba301b32eeb0853766446abc42bed","abstract_canon_sha256":"f5e6534aac7f5fa3791dab4256e68a4a50f6a77fa7636a398ce1d2f728efd43b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:43.085081Z","signature_b64":"wbHkVP3YYkz01hzCFhP6bLF3wcE1sk+5nXAzzYwFnPyAdnFuv/DzV21D7AP8itXiMh2zBnYEOqH2Tq2En+QKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b07f5082680ed6fcfc3323f946e2153574a7d18f0ebc5f76eeba886127ef936","last_reissued_at":"2026-05-17T23:49:43.084542Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:43.084542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ceyuan Yang, Dahua Lin, Hui Zhou, Jianping Shi, Xinge Zhu","submitted_at":"2018-09-04T11:50:09Z","abstract_excerpt":"Due to the expensive and time-consuming annotations (e.g., segmentation) for real-world images, recent works in computer vision resort to synthetic data. However, the performance on the real image often drops significantly because of the domain shift between the synthetic data and the real images. In this setting, domain adaptation brings an appealing option. The effective approaches of domain adaptation shape the representations that (1) are discriminative for the main task and (2) have good generalization capability for domain shift. To this end, we propose a novel loss function, i.e., Conse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00903","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":""},"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":"1809.00903","created_at":"2026-05-17T23:49:43.084638+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.00903v2","created_at":"2026-05-17T23:49:43.084638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00903","created_at":"2026-05-17T23:49:43.084638+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/DMD7KCBGQDWW7T6DGI7ZI3RBKN","json":"https://pith.science/pith/DMD7KCBGQDWW7T6DGI7ZI3RBKN.json","graph_json":"https://pith.science/api/pith-number/DMD7KCBGQDWW7T6DGI7ZI3RBKN/graph.json","events_json":"https://pith.science/api/pith-number/DMD7KCBGQDWW7T6DGI7ZI3RBKN/events.json","paper":"https://pith.science/paper/DMD7KCBG"},"agent_actions":{"view_html":"https://pith.science/pith/DMD7KCBGQDWW7T6DGI7ZI3RBKN","download_json":"https://pith.science/pith/DMD7KCBGQDWW7T6DGI7ZI3RBKN.json","view_paper":"https://pith.science/paper/DMD7KCBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.00903&json=true","fetch_graph":"https://pith.science/api/pith-number/DMD7KCBGQDWW7T6DGI7ZI3RBKN/graph.json","fetch_events":"https://pith.science/api/pith-number/DMD7KCBGQDWW7T6DGI7ZI3RBKN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMD7KCBGQDWW7T6DGI7ZI3RBKN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMD7KCBGQDWW7T6DGI7ZI3RBKN/action/storage_attestation","attest_author":"https://pith.science/pith/DMD7KCBGQDWW7T6DGI7ZI3RBKN/action/author_attestation","sign_citation":"https://pith.science/pith/DMD7KCBGQDWW7T6DGI7ZI3RBKN/action/citation_signature","submit_replication":"https://pith.science/pith/DMD7KCBGQDWW7T6DGI7ZI3RBKN/action/replication_record"}},"created_at":"2026-05-17T23:49:43.084638+00:00","updated_at":"2026-05-17T23:49:43.084638+00:00"}