{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EFV3BCPNU3GNGNLLPZEJGAVEOP","short_pith_number":"pith:EFV3BCPN","schema_version":"1.0","canonical_sha256":"216bb089eda6ccd3356b7e489302a473faa37c160ec0a72a74d2dce085e0c95c","source":{"kind":"arxiv","id":"2001.04692","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gianluca Agresti, Marco Toldo, Pietro Zanuttigh, Umberto Michieli","submitted_at":"2020-01-14T10:12:20Z","abstract_excerpt":"The supervised training of deep networks for semantic segmentation requires a huge amount of labeled real world data. To solve this issue, a commonly exploited workaround is to use synthetic data for training, but deep networks show a critical performance drop when analyzing data with slightly different statistical properties with respect to the training set. In this work, we propose a novel Unsupervised Domain Adaptation (UDA) strategy to address the domain shift issue between real world and synthetic representations. An adversarial model, based on the cycle consistency framework, performs th"},"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":"2001.04692","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-14T10:12:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a95e41c60d099d4ae54c67ecca6bd2efc53e91aeee9bcdd80c0fda1b11d60bf5","abstract_canon_sha256":"ae4e5cdae01d4cb5486e2f5a7b4b49dfdea4e48cc304df33228729b1ad96e7ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:47:29.086222Z","signature_b64":"eH/IfK4+h9S9/azjkwKmLibVudJJdUoRcvVQ83Fce2s9/dZJ/nhB5TqgpnIkOhJahV4vFyjCrbF+Bqv1v4qlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"216bb089eda6ccd3356b7e489302a473faa37c160ec0a72a74d2dce085e0c95c","last_reissued_at":"2026-07-05T00:47:29.085745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:47:29.085745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gianluca Agresti, Marco Toldo, Pietro Zanuttigh, Umberto Michieli","submitted_at":"2020-01-14T10:12:20Z","abstract_excerpt":"The supervised training of deep networks for semantic segmentation requires a huge amount of labeled real world data. To solve this issue, a commonly exploited workaround is to use synthetic data for training, but deep networks show a critical performance drop when analyzing data with slightly different statistical properties with respect to the training set. In this work, we propose a novel Unsupervised Domain Adaptation (UDA) strategy to address the domain shift issue between real world and synthetic representations. An adversarial model, based on the cycle consistency framework, performs th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.04692","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/2001.04692/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":"2001.04692","created_at":"2026-07-05T00:47:29.085814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.04692v2","created_at":"2026-07-05T00:47:29.085814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.04692","created_at":"2026-07-05T00:47:29.085814+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFV3BCPNU3GN","created_at":"2026-07-05T00:47:29.085814+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFV3BCPNU3GNGNLL","created_at":"2026-07-05T00:47:29.085814+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFV3BCPN","created_at":"2026-07-05T00:47:29.085814+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/EFV3BCPNU3GNGNLLPZEJGAVEOP","json":"https://pith.science/pith/EFV3BCPNU3GNGNLLPZEJGAVEOP.json","graph_json":"https://pith.science/api/pith-number/EFV3BCPNU3GNGNLLPZEJGAVEOP/graph.json","events_json":"https://pith.science/api/pith-number/EFV3BCPNU3GNGNLLPZEJGAVEOP/events.json","paper":"https://pith.science/paper/EFV3BCPN"},"agent_actions":{"view_html":"https://pith.science/pith/EFV3BCPNU3GNGNLLPZEJGAVEOP","download_json":"https://pith.science/pith/EFV3BCPNU3GNGNLLPZEJGAVEOP.json","view_paper":"https://pith.science/paper/EFV3BCPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.04692&json=true","fetch_graph":"https://pith.science/api/pith-number/EFV3BCPNU3GNGNLLPZEJGAVEOP/graph.json","fetch_events":"https://pith.science/api/pith-number/EFV3BCPNU3GNGNLLPZEJGAVEOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFV3BCPNU3GNGNLLPZEJGAVEOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFV3BCPNU3GNGNLLPZEJGAVEOP/action/storage_attestation","attest_author":"https://pith.science/pith/EFV3BCPNU3GNGNLLPZEJGAVEOP/action/author_attestation","sign_citation":"https://pith.science/pith/EFV3BCPNU3GNGNLLPZEJGAVEOP/action/citation_signature","submit_replication":"https://pith.science/pith/EFV3BCPNU3GNGNLLPZEJGAVEOP/action/replication_record"}},"created_at":"2026-07-05T00:47:29.085814+00:00","updated_at":"2026-07-05T00:47:29.085814+00:00"}