{"id":"W1918392599","doi":"10.1109/cvpr.2015.7298962","title":"DEEP-CARVING: Discovering visual attributes by carving deep neural nets","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Carving; Task (project management); Class (philosophy); Feature (linguistics); Deep learning; Visualization; Pattern recognition (psychology); Image (mathematics); Deep neural networks; Machine learning; Noun; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002513676,0.000232662,0.0002375446,0.00007902368,0.0001229129,0.0003694947,0.0009175673,0.00007140011,0.00001099997],"category_scores_gemma":[0.0002019157,0.0002010657,0.00008009709,0.0004480835,0.00004901159,0.002270331,0.0008512249,0.0001906505,0.000031735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001024615,"about_ca_system_score_gemma":0.0000350034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009648513,"about_ca_topic_score_gemma":0.0000188949,"domain_scores_codex":[0.99826,0.00005566328,0.0002778398,0.0004951281,0.000396375,0.0005150065],"domain_scores_gemma":[0.9989266,0.0001029176,0.00009101746,0.0004771187,0.0001376421,0.0002646795],"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":[0.00005317458,0.0003399581,0.01693102,0.00005890284,0.00008087379,0.0002195174,0.002395252,0.001796791,0.040022,0.0216949,0.02708557,0.889322],"study_design_scores_gemma":[0.0006703489,0.0005413158,0.0007279071,0.00003336652,0.00001345048,0.00007531396,0.0003530347,0.7259057,0.2393695,0.005186235,0.02615962,0.0009641753],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007444738,0.0009839882,0.9872494,0.0004947851,0.0002505014,0.0001576541,0.000001112003,0.0008150223,0.002602808],"genre_scores_gemma":[0.914919,0.00003144502,0.08377489,0.0007638485,0.00009981444,0.0000137425,0.000008312749,0.00002312932,0.0003658646],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9074742,"threshold_uncertainty_score":0.819922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02818055714190801,"score_gpt":0.2999601822645706,"score_spread":0.2717796251226625,"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."}}