{"id":"W3014285644","doi":"10.48550/arxiv.2004.01735","title":"Unsupervised Domain Adaptation with Progressive Domain Augmentation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Domain (mathematical analysis); Computer science; Subspace topology; Exploit; Domain adaptation; Artificial intelligence; Adaptation (eye); Divergence (linguistics); Interpolation (computer graphics); Pattern recognition (psychology); Image (mathematics); Mathematics; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007869742,0.0007929021,0.0008475622,0.0009091279,0.0004803004,0.0006739194,0.001254323,0.0008480913,0.001380562],"category_scores_gemma":[0.002654154,0.0002970551,0.0009542956,0.0009535604,0.0009236755,0.001684744,0.002038563,0.001758558,0.001134907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003666519,"about_ca_system_score_gemma":0.0007758319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001390641,"about_ca_topic_score_gemma":0.00216564,"domain_scores_codex":[0.9993256,0.0001796141,0.00002399333,0.0002716267,0.0001338211,0.00006536184],"domain_scores_gemma":[0.9988874,0.0003738837,0.00008040127,0.0003797578,0.0002150493,0.00006354134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003972765,0.0004575996,0.003608421,0.0002470222,0.0001576677,0.000291283,0.0004083418,0.180825,0.1077897,0.01409979,0.0103393,0.6813784],"study_design_scores_gemma":[0.00002503037,0.0001020141,0.0009149426,0.00001770594,0.00002189476,0.0002654113,0.00009043195,0.9488747,0.02607341,0.01803519,0.005545424,0.00003390803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02249596,0.0002495147,0.9741255,0.00007254607,0.00005697292,0.00006736034,0.0001084986,0.001462672,0.001360975],"genre_scores_gemma":[0.4650494,0.000352345,0.5274273,0.0003486345,0.00009292351,0.0002462626,0.001554598,0.000305468,0.004623064],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001390641,"threshold_uncertainty_score":0.004618466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08486027176570617,"score_gpt":0.1941086992223512,"score_spread":0.109248427456645,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}