{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001952146,0.00009924112,0.00009016803,0.00009168216,0.00006625192,0.0002106507,0.0004596307,0.00003676248,0.0007312545],"category_scores_gemma":[0.00001999243,0.00008630264,0.0000416433,0.0002739508,0.00004518341,0.0009288143,0.0001078605,0.00006617718,0.0002698803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004336607,"about_ca_system_score_gemma":0.00003141514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002182563,"about_ca_topic_score_gemma":0.000009565483,"domain_scores_codex":[0.9988927,0.00005154515,0.0002420915,0.000272042,0.0003462426,0.0001953332],"domain_scores_gemma":[0.9994259,0.00004557612,0.00004720531,0.0003357627,0.00007577967,0.00006973763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000245774,0.0001341975,0.0005338173,0.00001637068,0.000006090617,0.00002468973,0.000177694,0.000002648214,0.6873722,0.02133448,0.09909204,0.1913033],"study_design_scores_gemma":[0.0003074937,0.00004539538,0.001834061,0.000006036197,0.000002915544,0.000007337437,0.00003870914,0.007139837,0.9848249,0.004939329,0.0006913675,0.0001626284],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003236451,0.00001534653,0.9641073,0.00118659,0.0001115203,0.0001898572,9.706922e-7,0.0007597898,0.03039215],"genre_scores_gemma":[0.03768655,0.000005567538,0.9565721,0.001640729,0.00007402123,0.00003643837,0.00001908329,0.000007583757,0.003957999],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2974527,"threshold_uncertainty_score":0.8006724,"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."}}