{"id":"W2141197099","doi":"10.1109/cvpr.2006.333","title":"Weakly Supervised Top-down Image Segmentation","year":2006,"lang":"en","type":"article","venue":"","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Segmentation; Computer science; Artificial intelligence; Scale-space segmentation; Segmentation-based object categorization; Image segmentation; Set (abstract data type); Pattern recognition (psychology); Minimum spanning tree-based segmentation; Image (mathematics); Training set; Top-down and bottom-up design; Computer vision","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001662816,0.001462185,0.002212405,0.001479834,0.0007575835,0.001996155,0.003025165,0.002085586,0.003555496],"category_scores_gemma":[0.004940854,0.001058926,0.001485627,0.001186571,0.002092332,0.002184249,0.002081404,0.001889321,0.002404873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00101703,"about_ca_system_score_gemma":0.001289641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001879213,"about_ca_topic_score_gemma":0.00319811,"domain_scores_codex":[0.9983106,0.0003969177,0.0001085371,0.0005874913,0.0004485986,0.0001479213],"domain_scores_gemma":[0.9964584,0.001310732,0.0003578302,0.0009385489,0.0007719782,0.0001625923],"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":[0.0005473785,0.0001986533,0.001630401,0.0007824286,0.0002012022,0.0003399412,0.0004010485,0.2602327,0.1219043,0.0193902,0.00808686,0.5862848],"study_design_scores_gemma":[0.0000118963,0.00005872465,0.000415373,0.00002168109,0.00002075771,0.00009857411,0.00003257608,0.9632639,0.02008075,0.01367242,0.002306143,0.00001719016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00736888,0.0002028514,0.9899501,0.0001034887,0.0000201581,0.00007810123,0.00008057643,0.001238722,0.0009571385],"genre_scores_gemma":[0.1802225,0.0003702272,0.813107,0.0003000116,0.00009800385,0.0002158927,0.0008775517,0.0005779226,0.004231052],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003555496,"threshold_uncertainty_score":0.01189435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00828248159199732,"score_gpt":0.2605544460249735,"score_spread":0.2522719644329762,"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."}}