{"id":"W4282977123","doi":"10.1109/cvprw56347.2022.00445","title":"AuxMix: Semi-Supervised Learning with Unconstrained Unlabeled Data","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Semi-supervised learning; Computer science; Labeled data; Artificial intelligence; Training set; Entropy (arrow of time); Machine learning; Set (abstract data type); Data set; Co-training; Supervised learning; Pattern recognition (psychology); Data mining; Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001052617,0.0005089629,0.0004960542,0.0004006328,0.001165553,0.0009064539,0.001556111,0.0001206966,0.001960215],"category_scores_gemma":[0.00003300397,0.0004735424,0.00008642465,0.0009304149,0.0001192029,0.0008390574,0.001186459,0.00140113,0.0001678268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007701001,"about_ca_system_score_gemma":0.0001912162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002913751,"about_ca_topic_score_gemma":0.00003431333,"domain_scores_codex":[0.9952457,0.0009709834,0.000588475,0.001550788,0.001028391,0.0006156946],"domain_scores_gemma":[0.9975093,0.0004979852,0.0003600319,0.001058542,0.0002216451,0.0003525244],"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":[0.0001356316,0.0002317618,0.0006740728,0.00003267312,0.00007312629,0.0001561951,0.001651497,0.001941233,0.0003978211,0.0003988846,0.002883786,0.9914233],"study_design_scores_gemma":[0.002970275,0.001368361,0.001053353,0.0003001027,0.00003315276,0.0002571302,0.0009609234,0.9806208,0.00006527243,0.0005017151,0.01096132,0.0009076026],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0630527,0.00006547521,0.9298163,0.002524439,0.00130431,0.0005462961,0.00008248734,0.0005721236,0.002035854],"genre_scores_gemma":[0.9783435,0.0001198503,0.01552025,0.004028349,0.000217579,0.00008827668,0.0008721644,0.00005498156,0.0007550015],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9905157,"threshold_uncertainty_score":0.9997717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06501587995759424,"score_gpt":0.2747724017184636,"score_spread":0.2097565217608693,"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."}}