{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SMODXAVUZAEPMEWYXUWCI46TB3","short_pith_number":"pith:SMODXAVU","schema_version":"1.0","canonical_sha256":"931c3b82b4c808f612d8bd2c2473d30edb73646ffcd8b9473d9b7ef9c7aa4ec6","source":{"kind":"arxiv","id":"2304.13615","version":2},"attestation_state":"computed","paper":{"title":"Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dengxin Dai, Luc Van Gool, Lukas Hoyer","submitted_at":"2023-04-26T15:18:45Z","abstract_excerpt":"Unsupervised domain adaptation (UDA) and domain generalization (DG) enable machine learning models trained on a source domain to perform well on unlabeled or even unseen target domains. As previous UDA&DG semantic segmentation methods are mostly based on outdated networks, we benchmark more recent architectures, reveal the potential of Transformers, and design the DAFormer network tailored for UDA&DG. It is enabled by three training strategies to avoid overfitting to the source domain: While (1) Rare Class Sampling mitigates the bias toward common source domain classes, (2) a Thing-Class Image"},"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":"2304.13615","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-26T15:18:45Z","cross_cats_sorted":[],"title_canon_sha256":"dab072c72581f865082484ed770f60466132000b262aecc0deb3f186710fa7cd","abstract_canon_sha256":"82a9f2bfdee7a2a5229099a4da8126fd087eb5ac3a073d6348e802985bdb235e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:38.322857Z","signature_b64":"SD02kR2HS5f/T58l/EqlXseLT9hPVNNHDGdGtdxPFRQpSnqgD2IRNnxLrUcobn/wtHBBUZtEzhojt7dj3nHkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"931c3b82b4c808f612d8bd2c2473d30edb73646ffcd8b9473d9b7ef9c7aa4ec6","last_reissued_at":"2026-07-05T06:54:38.322374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:38.322374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dengxin Dai, Luc Van Gool, Lukas Hoyer","submitted_at":"2023-04-26T15:18:45Z","abstract_excerpt":"Unsupervised domain adaptation (UDA) and domain generalization (DG) enable machine learning models trained on a source domain to perform well on unlabeled or even unseen target domains. As previous UDA&DG semantic segmentation methods are mostly based on outdated networks, we benchmark more recent architectures, reveal the potential of Transformers, and design the DAFormer network tailored for UDA&DG. It is enabled by three training strategies to avoid overfitting to the source domain: While (1) Rare Class Sampling mitigates the bias toward common source domain classes, (2) a Thing-Class Image"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13615","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/2304.13615/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":"2304.13615","created_at":"2026-07-05T06:54:38.322435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.13615v2","created_at":"2026-07-05T06:54:38.322435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13615","created_at":"2026-07-05T06:54:38.322435+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMODXAVUZAEP","created_at":"2026-07-05T06:54:38.322435+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMODXAVUZAEPMEWY","created_at":"2026-07-05T06:54:38.322435+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMODXAVU","created_at":"2026-07-05T06:54:38.322435+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/SMODXAVUZAEPMEWYXUWCI46TB3","json":"https://pith.science/pith/SMODXAVUZAEPMEWYXUWCI46TB3.json","graph_json":"https://pith.science/api/pith-number/SMODXAVUZAEPMEWYXUWCI46TB3/graph.json","events_json":"https://pith.science/api/pith-number/SMODXAVUZAEPMEWYXUWCI46TB3/events.json","paper":"https://pith.science/paper/SMODXAVU"},"agent_actions":{"view_html":"https://pith.science/pith/SMODXAVUZAEPMEWYXUWCI46TB3","download_json":"https://pith.science/pith/SMODXAVUZAEPMEWYXUWCI46TB3.json","view_paper":"https://pith.science/paper/SMODXAVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.13615&json=true","fetch_graph":"https://pith.science/api/pith-number/SMODXAVUZAEPMEWYXUWCI46TB3/graph.json","fetch_events":"https://pith.science/api/pith-number/SMODXAVUZAEPMEWYXUWCI46TB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMODXAVUZAEPMEWYXUWCI46TB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMODXAVUZAEPMEWYXUWCI46TB3/action/storage_attestation","attest_author":"https://pith.science/pith/SMODXAVUZAEPMEWYXUWCI46TB3/action/author_attestation","sign_citation":"https://pith.science/pith/SMODXAVUZAEPMEWYXUWCI46TB3/action/citation_signature","submit_replication":"https://pith.science/pith/SMODXAVUZAEPMEWYXUWCI46TB3/action/replication_record"}},"created_at":"2026-07-05T06:54:38.322435+00:00","updated_at":"2026-07-05T06:54:38.322435+00:00"}