{"id":"W4416303086","doi":"10.1016/j.atech.2025.101637","title":"Pipeline to detect Colorado Potato Beetles as tiny objects under field conditions in real-time using deep learning and transfer learning techniques","year":2025,"lang":"en","type":"article","venue":"Smart Agricultural Technology","topic":"Smart Agriculture and AI","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Transfer of learning; Preprocessor; Object detection; Deep learning; Robustness (evolution); Pipeline (software); Image processing; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001730645,0.0003326292,0.0004416493,0.0001612075,0.0004765232,0.00008468128,0.0002601343,0.0005225539,0.0001333844],"category_scores_gemma":[0.0001791771,0.0001404711,0.0001004958,0.001976791,0.000102866,0.0001490871,0.0001783315,0.0006346708,0.0000420756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008060737,"about_ca_system_score_gemma":0.00001308671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00070145,"about_ca_topic_score_gemma":0.003463396,"domain_scores_codex":[0.9981981,0.0001226561,0.0003928279,0.0005793315,0.0001518168,0.0005552989],"domain_scores_gemma":[0.9993355,0.0003051556,0.00006179865,0.00006075475,0.0001347901,0.0001020211],"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":[0.0000298303,0.00003835786,0.005728736,0.000009394779,0.00002162388,0.00001511392,0.0001122846,0.00003869222,0.9791118,0.0006644041,0.00064836,0.01358143],"study_design_scores_gemma":[0.0008505536,0.00243676,0.2392213,0.0005686858,0.0001694051,0.000316398,0.01339131,0.0001141667,0.6938727,0.006960887,0.04038698,0.001710775],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9901007,0.0002388638,0.00002834858,0.005839215,0.00007484318,0.0005589142,0.000004808962,0.0006694568,0.002484877],"genre_scores_gemma":[0.9962938,0.0001932603,0.0005737475,0.000527219,0.0001078632,0.00009222789,0.0000668295,0.00000285607,0.002142165],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.285239,"threshold_uncertainty_score":0.5728245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007642789995346978,"score_gpt":0.2457245509591281,"score_spread":0.2380817609637811,"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."}}