{"id":"W3118254750","doi":"","title":"Improving Object Detection with MatrixNets","year":2020,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Waterloo","keywords":"Computer science; Artificial intelligence; Information retrieval","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":[0.00005854537,0.0001863348,0.0002502541,0.0002034117,0.0001883634,0.00005403311,0.0005106137,0.0001973693,0.0000407745],"category_scores_gemma":[0.000006654934,0.0001906935,0.00009797348,0.0002937769,0.00002371317,0.0005467153,0.00008428236,0.0002358964,0.0001073584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004089781,"about_ca_system_score_gemma":0.00008722445,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009677968,"about_ca_topic_score_gemma":0.01528831,"domain_scores_codex":[0.9989598,0.00004342499,0.00008479653,0.0004293743,0.0002921737,0.0001904744],"domain_scores_gemma":[0.9992166,0.0000175994,0.0002584876,0.000272233,0.000141597,0.00009350196],"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":[0.001116151,0.0001633967,0.0001386552,0.001749269,0.0002868767,0.0003857441,0.251848,0.0001188167,0.3866907,0.0002820507,0.00237391,0.3548464],"study_design_scores_gemma":[0.004543036,0.002645865,0.00549011,0.001746134,0.0005736356,0.00005189782,0.2595523,0.0553326,0.6626785,0.0006257597,0.00408102,0.002679146],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9825191,0.00006248177,0.01511627,0.0004283579,0.0004243877,0.0003074482,0.000008373721,0.0002655943,0.0008680107],"genre_scores_gemma":[0.7204983,0.0001418887,0.04841754,0.00007799651,0.0001053616,0.000002053451,0.0004280673,0.00005985345,0.2302689],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3521672,"threshold_uncertainty_score":0.9969167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006729335994791593,"score_gpt":0.1783486197140839,"score_spread":0.1716192837192923,"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."}}