{"id":"W2112717538","doi":"10.1145/1553374.1553413","title":"Learning to segment from a few well-selected training images","year":2009,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Magyar Tudományos Akadémia Számítástechnikai és Automatizálási Kutatóintézet","keywords":"Computer science; Artificial intelligence; Discriminative model; Market segmentation; Segmentation; Image segmentation; Oracle; Pattern recognition (psychology); Computer vision; Task (project management); Image (mathematics); Field (mathematics); Contextual image classification; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001969605,0.0001402887,0.0001589935,0.00009522971,0.0001711817,0.0002538084,0.0005076451,0.00003489877,0.000169779],"category_scores_gemma":[0.00008445165,0.000121602,0.00004223953,0.0005344157,0.000006668429,0.0001694912,0.0000892901,0.0002795454,0.0003378274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002319561,"about_ca_system_score_gemma":0.00003852966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001800739,"about_ca_topic_score_gemma":0.000004136338,"domain_scores_codex":[0.9987531,0.00009189449,0.0001602323,0.000416688,0.0002379893,0.0003400935],"domain_scores_gemma":[0.9994144,0.00007753113,0.00004228555,0.0002560936,0.0000490049,0.0001607272],"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":[0.000005244536,0.00004739423,0.0006733011,0.000001396591,0.00001491155,0.00003075521,0.00622041,0.004362982,0.005819997,0.001061801,0.003738708,0.9780231],"study_design_scores_gemma":[0.001860799,0.001946983,0.1407579,0.0001238542,0.00001863955,0.00003956302,0.001005554,0.7739691,0.01319066,0.003155129,0.06257112,0.001360792],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09621354,0.00005492564,0.871683,0.007261166,0.0001696848,0.0001098796,5.092291e-7,0.001016477,0.02349079],"genre_scores_gemma":[0.7728056,0.000003336591,0.2197905,0.001570497,0.0001466197,0.000003441157,0.000004394455,0.00000682956,0.005668784],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9766623,"threshold_uncertainty_score":0.4958788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009406377697098126,"score_gpt":0.2447585415135107,"score_spread":0.2353521638164126,"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."}}