{"id":"W1854500361","doi":"10.1109/crv.2005.28","title":"Comparing Classification Metrics for Labeling Segmented Remote Sensing Images","year":2005,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Metric (unit); A priori and a posteriori; Artificial intelligence; Segmentation; Pixel; Pattern recognition (psychology); Contextual image classification; Object (grammar); Image segmentation; Constraint (computer-aided design); Voting; Image (mathematics); Scheme (mathematics); Data mining; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01478839,0.001360564,0.00205376,0.009179726,0.0008894543,0.00352757,0.001575001,0.002383573,0.001019444],"category_scores_gemma":[0.04780592,0.0003569538,0.001073095,0.004491921,0.001374087,0.00341325,0.00183408,0.001076691,0.0004364854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003077051,"about_ca_system_score_gemma":0.001135911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004504388,"about_ca_topic_score_gemma":0.005023001,"domain_scores_codex":[0.9896401,0.004354439,0.001109742,0.001149051,0.003162334,0.0005842886],"domain_scores_gemma":[0.9612936,0.02579343,0.00182831,0.002652988,0.007670526,0.0007609702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002874128,0.0004048423,0.01703381,0.00115982,0.0007429644,0.0001141766,0.0007055718,0.1848328,0.02139183,0.01816689,0.006317001,0.7462562],"study_design_scores_gemma":[0.0001340156,0.001709064,0.01737633,0.0001560914,0.0002694233,0.0002439369,0.0007879925,0.9236755,0.02845344,0.02269238,0.004291638,0.0002101821],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4818438,0.003864512,0.5030128,0.0006072042,0.0002628956,0.0006850449,0.0008569724,0.00185101,0.007015679],"genre_scores_gemma":[0.690529,0.0006131405,0.3044733,0.0001099824,0.00005930417,0.0003118877,0.002313957,0.000319461,0.001270085],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01478839,"threshold_uncertainty_score":0.0782094,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07052530705521581,"score_gpt":0.309896343130112,"score_spread":0.2393710360748962,"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."}}