{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KVEALAW6MEX55U76AFU2SCEMAQ","short_pith_number":"pith:KVEALAW6","schema_version":"1.0","canonical_sha256":"55480582de612fded3fe0169a9088c04252a94fbf53316252326adb86411a06e","source":{"kind":"arxiv","id":"1807.09834","version":1},"attestation_state":"computed","paper":{"title":"Applying Domain Randomization to Synthetic Data for Object Category Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alexandre Bernardino, Atabak Dehban, Jo\\~ao Borrego, Jos\\'e Santos-Victor, Plinio Moreno, Rui Figueiredo","submitted_at":"2018-07-16T15:08:57Z","abstract_excerpt":"Recent advances in deep learning-based object detection techniques have revolutionized their applicability in several fields. However, since these methods rely on unwieldy and large amounts of data, a common practice is to download models pre-trained on standard datasets and fine-tune them for specific application domains with a small set of domain relevant images. In this work, we show that using synthetic datasets that are not necessarily photo-realistic can be a better alternative to simply fine-tune pre-trained networks. Specifically, our results show an impressive 25% improvement in the m"},"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":"1807.09834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-16T15:08:57Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7125b6e4d7a1144bb16bebee1312a65ab08efcc9c6cf984cf05ed2b626096f8f","abstract_canon_sha256":"11c6cae6d0e036e01f70ea5050944db61ca1c8e3662a6ef5bdb0cc086eaced22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:46.460588Z","signature_b64":"61i5BnUQaTHwBEfdq/r7OdSlrq4HVMm+ItBTypBF7OgLjAqNpif/gitFJTQqwN/+zoPCX2a0neAce/7bjMlPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55480582de612fded3fe0169a9088c04252a94fbf53316252326adb86411a06e","last_reissued_at":"2026-05-18T00:09:46.459928Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:46.459928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Applying Domain Randomization to Synthetic Data for Object Category Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alexandre Bernardino, Atabak Dehban, Jo\\~ao Borrego, Jos\\'e Santos-Victor, Plinio Moreno, Rui Figueiredo","submitted_at":"2018-07-16T15:08:57Z","abstract_excerpt":"Recent advances in deep learning-based object detection techniques have revolutionized their applicability in several fields. However, since these methods rely on unwieldy and large amounts of data, a common practice is to download models pre-trained on standard datasets and fine-tune them for specific application domains with a small set of domain relevant images. In this work, we show that using synthetic datasets that are not necessarily photo-realistic can be a better alternative to simply fine-tune pre-trained networks. Specifically, our results show an impressive 25% improvement in the m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09834","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":"1807.09834","created_at":"2026-05-18T00:09:46.460017+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.09834v1","created_at":"2026-05-18T00:09:46.460017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09834","created_at":"2026-05-18T00:09:46.460017+00:00"},{"alias_kind":"pith_short_12","alias_value":"KVEALAW6MEX5","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KVEALAW6MEX55U76","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KVEALAW6","created_at":"2026-05-18T12:32:33.847187+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/KVEALAW6MEX55U76AFU2SCEMAQ","json":"https://pith.science/pith/KVEALAW6MEX55U76AFU2SCEMAQ.json","graph_json":"https://pith.science/api/pith-number/KVEALAW6MEX55U76AFU2SCEMAQ/graph.json","events_json":"https://pith.science/api/pith-number/KVEALAW6MEX55U76AFU2SCEMAQ/events.json","paper":"https://pith.science/paper/KVEALAW6"},"agent_actions":{"view_html":"https://pith.science/pith/KVEALAW6MEX55U76AFU2SCEMAQ","download_json":"https://pith.science/pith/KVEALAW6MEX55U76AFU2SCEMAQ.json","view_paper":"https://pith.science/paper/KVEALAW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.09834&json=true","fetch_graph":"https://pith.science/api/pith-number/KVEALAW6MEX55U76AFU2SCEMAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KVEALAW6MEX55U76AFU2SCEMAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KVEALAW6MEX55U76AFU2SCEMAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KVEALAW6MEX55U76AFU2SCEMAQ/action/storage_attestation","attest_author":"https://pith.science/pith/KVEALAW6MEX55U76AFU2SCEMAQ/action/author_attestation","sign_citation":"https://pith.science/pith/KVEALAW6MEX55U76AFU2SCEMAQ/action/citation_signature","submit_replication":"https://pith.science/pith/KVEALAW6MEX55U76AFU2SCEMAQ/action/replication_record"}},"created_at":"2026-05-18T00:09:46.460017+00:00","updated_at":"2026-05-18T00:09:46.460017+00:00"}