{"id":"W4386065385","doi":"10.1109/cvpr52729.2023.01878","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","year":2023,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":363,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Shot (pellet); Anomaly (physics); Task (project management); Pattern recognition (psychology); Focus (optics); Computer vision; Field (mathematics); Image segmentation; Mathematics; Engineering","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":[0.0001425856,0.00006564665,0.00005592897,0.0001149917,0.000168855,0.0001102619,0.0001941412,0.00004007378,0.00001834383],"category_scores_gemma":[0.000005920694,0.00006166208,0.00002143325,0.0006224528,0.00002691853,0.0003205856,0.0001003424,0.00004470813,0.0001798523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000199761,"about_ca_system_score_gemma":0.00001330681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002291329,"about_ca_topic_score_gemma":0.000004436203,"domain_scores_codex":[0.9993595,0.00001673196,0.0001370632,0.0002619026,0.0001081515,0.0001166569],"domain_scores_gemma":[0.9995542,0.00003216058,0.00004886064,0.0002771722,0.00003747493,0.00005015382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000002541695,0.00004625033,0.0058196,0.00001395811,0.00001160635,0.000001746549,0.0003361341,0.00001436798,0.1123512,0.6388455,0.01664817,0.2259089],"study_design_scores_gemma":[0.000515412,0.0002298429,0.4520103,0.00001398112,0.0000154577,0.00003860226,0.0003809917,0.3390429,0.09031168,0.06369972,0.05311595,0.0006251104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06214165,0.000009401067,0.9265323,0.002192412,0.00004918711,0.0001943344,0.000001281006,0.001225035,0.007654363],"genre_scores_gemma":[0.9600276,0.00005511185,0.0369852,0.0002506262,0.00002239537,0.0001063504,0.000009215139,0.00000555084,0.002537889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.897886,"threshold_uncertainty_score":0.2514507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04701788183755889,"score_gpt":0.3003302529879949,"score_spread":0.253312371150436,"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."}}