{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FETQPZM53HI7RQQJZ36KZPDQSI","short_pith_number":"pith:FETQPZM5","schema_version":"1.0","canonical_sha256":"292707e59dd9d1f8c209cefcacbc709202e51ba73d8d74bc250e21d81e8a1d88","source":{"kind":"arxiv","id":"1711.09082","version":1},"attestation_state":"computed","paper":{"title":"Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yong Jae Lee, Zhongzheng Ren","submitted_at":"2017-11-24T18:55:01Z","abstract_excerpt":"In human learning, it is common to use multiple sources of information jointly. However, most existing feature learning approaches learn from only a single task. In this paper, we propose a novel multi-task deep network to learn generalizable high-level visual representations. Since multi-task learning requires annotations for multiple properties of the same training instance, we look to synthetic images to train our network. To overcome the domain difference between real and synthetic data, we employ an unsupervised feature space domain adaptation method based on adversarial learning. Given a"},"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":"1711.09082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-24T18:55:01Z","cross_cats_sorted":[],"title_canon_sha256":"31489569e17acaa7241fc7ac849d88129e782f4b187d9f05cbef376c13f21f07","abstract_canon_sha256":"695dcc905184116737b9a93812d27bce6de1ac0c5a3a3d90835c63abf7002740"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:41.248872Z","signature_b64":"e1aBKzZjw5voOgKHEfARxhUaRG6Cf3adVekhIdqZFso6gwaNqXBw3WRYd/VGy1C0I9TB5Sm+yGku8rMWhmKMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"292707e59dd9d1f8c209cefcacbc709202e51ba73d8d74bc250e21d81e8a1d88","last_reissued_at":"2026-05-18T00:29:41.248244Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:41.248244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yong Jae Lee, Zhongzheng Ren","submitted_at":"2017-11-24T18:55:01Z","abstract_excerpt":"In human learning, it is common to use multiple sources of information jointly. However, most existing feature learning approaches learn from only a single task. In this paper, we propose a novel multi-task deep network to learn generalizable high-level visual representations. Since multi-task learning requires annotations for multiple properties of the same training instance, we look to synthetic images to train our network. To overcome the domain difference between real and synthetic data, we employ an unsupervised feature space domain adaptation method based on adversarial learning. Given a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09082","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":""},"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":"1711.09082","created_at":"2026-05-18T00:29:41.248349+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.09082v1","created_at":"2026-05-18T00:29:41.248349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09082","created_at":"2026-05-18T00:29:41.248349+00:00"},{"alias_kind":"pith_short_12","alias_value":"FETQPZM53HI7","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FETQPZM53HI7RQQJ","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FETQPZM5","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.03402","citing_title":"Distill-2MD-MTL: Data Distillation based on Multi-Dataset Multi-Domain Multi-Task Frame Work to Solve Face Related Tasksks, Multi Task Learning, Semi-Supervised Learning","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11004","citing_title":"Don't Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FETQPZM53HI7RQQJZ36KZPDQSI","json":"https://pith.science/pith/FETQPZM53HI7RQQJZ36KZPDQSI.json","graph_json":"https://pith.science/api/pith-number/FETQPZM53HI7RQQJZ36KZPDQSI/graph.json","events_json":"https://pith.science/api/pith-number/FETQPZM53HI7RQQJZ36KZPDQSI/events.json","paper":"https://pith.science/paper/FETQPZM5"},"agent_actions":{"view_html":"https://pith.science/pith/FETQPZM53HI7RQQJZ36KZPDQSI","download_json":"https://pith.science/pith/FETQPZM53HI7RQQJZ36KZPDQSI.json","view_paper":"https://pith.science/paper/FETQPZM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.09082&json=true","fetch_graph":"https://pith.science/api/pith-number/FETQPZM53HI7RQQJZ36KZPDQSI/graph.json","fetch_events":"https://pith.science/api/pith-number/FETQPZM53HI7RQQJZ36KZPDQSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FETQPZM53HI7RQQJZ36KZPDQSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FETQPZM53HI7RQQJZ36KZPDQSI/action/storage_attestation","attest_author":"https://pith.science/pith/FETQPZM53HI7RQQJZ36KZPDQSI/action/author_attestation","sign_citation":"https://pith.science/pith/FETQPZM53HI7RQQJZ36KZPDQSI/action/citation_signature","submit_replication":"https://pith.science/pith/FETQPZM53HI7RQQJZ36KZPDQSI/action/replication_record"}},"created_at":"2026-05-18T00:29:41.248349+00:00","updated_at":"2026-05-18T00:29:41.248349+00:00"}