{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NFYTF5BA2FD2AI2RYDHH64GZI2","short_pith_number":"pith:NFYTF5BA","schema_version":"1.0","canonical_sha256":"697132f420d147a02351c0ce7f70d946a81ac468038a6c617d7d9dae81d04330","source":{"kind":"arxiv","id":"1810.03756","version":3},"attestation_state":"computed","paper":{"title":"SPIGAN: Privileged Adversarial Learning from Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrien Gaidon, German Ros, Jie Li, Kuan-Hui Lee","submitted_at":"2018-10-09T00:17:24Z","abstract_excerpt":"Deep Learning for Computer Vision depends mainly on the source of supervision.Photo-realistic simulators can generate large-scale automatically labeled syntheticdata, but introduce a domain gap negatively impacting performance. We propose anew unsupervised domain adaptation algorithm, called SPIGAN, relying on Sim-ulator Privileged Information (PI) and Generative Adversarial Networks (GAN).We use internal data from the simulator as PI during the training of a target tasknetwork. We experimentally evaluate our approach on semantic segmentation. Wetrain the networks on real-world Cityscapes and "},"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":"1810.03756","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-09T00:17:24Z","cross_cats_sorted":[],"title_canon_sha256":"8eb7f7957b84ce7fd963c9d9489caa7c1e75ed4180c2a73791479b854266f12c","abstract_canon_sha256":"fb063ff3cebe41cef838759690b4341df8b1ba36b90eb5e231d4b7aeeefd7d44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:50.568463Z","signature_b64":"IfP/c26Fk5ocoKngKnhhj+tpwAs1Jrhb6vKQwU5quXBg0qzKRKFjfHh4NJqz1VHSvilFe2dGSpj93rVad8j2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"697132f420d147a02351c0ce7f70d946a81ac468038a6c617d7d9dae81d04330","last_reissued_at":"2026-05-17T23:53:50.567724Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:50.567724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPIGAN: Privileged Adversarial Learning from Simulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrien Gaidon, German Ros, Jie Li, Kuan-Hui Lee","submitted_at":"2018-10-09T00:17:24Z","abstract_excerpt":"Deep Learning for Computer Vision depends mainly on the source of supervision.Photo-realistic simulators can generate large-scale automatically labeled syntheticdata, but introduce a domain gap negatively impacting performance. We propose anew unsupervised domain adaptation algorithm, called SPIGAN, relying on Sim-ulator Privileged Information (PI) and Generative Adversarial Networks (GAN).We use internal data from the simulator as PI during the training of a target tasknetwork. We experimentally evaluate our approach on semantic segmentation. Wetrain the networks on real-world Cityscapes and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03756","kind":"arxiv","version":3},"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":"1810.03756","created_at":"2026-05-17T23:53:50.567849+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.03756v3","created_at":"2026-05-17T23:53:50.567849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03756","created_at":"2026-05-17T23:53:50.567849+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFYTF5BA2FD2","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFYTF5BA2FD2AI2R","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFYTF5BA","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2405.15314","citing_title":"Output-Constrained Decision Trees","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2602.04583","citing_title":"PEPR: Privileged Event-based Predictive Regularization for Domain Generalization","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFYTF5BA2FD2AI2RYDHH64GZI2","json":"https://pith.science/pith/NFYTF5BA2FD2AI2RYDHH64GZI2.json","graph_json":"https://pith.science/api/pith-number/NFYTF5BA2FD2AI2RYDHH64GZI2/graph.json","events_json":"https://pith.science/api/pith-number/NFYTF5BA2FD2AI2RYDHH64GZI2/events.json","paper":"https://pith.science/paper/NFYTF5BA"},"agent_actions":{"view_html":"https://pith.science/pith/NFYTF5BA2FD2AI2RYDHH64GZI2","download_json":"https://pith.science/pith/NFYTF5BA2FD2AI2RYDHH64GZI2.json","view_paper":"https://pith.science/paper/NFYTF5BA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.03756&json=true","fetch_graph":"https://pith.science/api/pith-number/NFYTF5BA2FD2AI2RYDHH64GZI2/graph.json","fetch_events":"https://pith.science/api/pith-number/NFYTF5BA2FD2AI2RYDHH64GZI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFYTF5BA2FD2AI2RYDHH64GZI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFYTF5BA2FD2AI2RYDHH64GZI2/action/storage_attestation","attest_author":"https://pith.science/pith/NFYTF5BA2FD2AI2RYDHH64GZI2/action/author_attestation","sign_citation":"https://pith.science/pith/NFYTF5BA2FD2AI2RYDHH64GZI2/action/citation_signature","submit_replication":"https://pith.science/pith/NFYTF5BA2FD2AI2RYDHH64GZI2/action/replication_record"}},"created_at":"2026-05-17T23:53:50.567849+00:00","updated_at":"2026-05-17T23:53:50.567849+00:00"}