{"id":"W2956356670","doi":"10.23919/mva.2019.8757886","title":"Exploring Better Food Detection via Transfer Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Chemical Sensor Technologies","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Transfer of learning; Object detection; Initialization; Artificial intelligence; Generalization; Task (project management); Perspective (graphical); Machine learning; Deep learning; Architecture; Artificial neural network; Contextual image classification; Object (grammar); Pattern recognition (psychology); Image (mathematics); 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":[0.000008582135,0.00008583503,0.00007914771,0.0000408632,0.00001567027,0.00000713209,0.00005922962,0.00005561884,0.00008361058],"category_scores_gemma":[0.000006173916,0.00008171544,0.00003064513,0.0000946169,0.000008108035,0.0002041314,0.000009499913,0.0002380453,0.0001957239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003829927,"about_ca_system_score_gemma":1.440046e-7,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001030406,"about_ca_topic_score_gemma":0.000002459743,"domain_scores_codex":[0.9995809,0.000002214314,0.00008058539,0.000105006,0.00006034763,0.0001709201],"domain_scores_gemma":[0.9998493,0.00002074982,0.000002604506,0.0001034494,0.000006488579,0.00001743438],"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":[0.000001214702,0.000001300941,0.0002212904,0.00001546039,0.000008947352,3.027975e-7,0.00002451821,0.01856505,0.9182728,0.00002630405,0.000001139763,0.06286167],"study_design_scores_gemma":[0.0001010611,0.00003800614,0.0001543686,0.000005287088,0.000002281389,0.000001649613,0.00007242341,0.005311019,0.9912448,0.0002195527,0.002727562,0.0001220187],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.900295,0.00002073283,0.09474012,0.0000180132,0.0001202486,0.00005517884,1.3145e-7,0.002199793,0.002550831],"genre_scores_gemma":[0.9990547,0.0000215048,0.0007634845,0.00001126562,0.00003112499,0.0000167942,5.077178e-7,0.00002778242,0.00007280775],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09875978,"threshold_uncertainty_score":0.3332259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02497530622566694,"score_gpt":0.1791347666103738,"score_spread":0.1541594603847068,"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."}}