{"id":"W4395069151","doi":"10.1007/s11263-024-02069-9","title":"Position, Padding and Predictions: A Deeper Look at Position Information in CNNs","year":2024,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph; York University; Toronto Metropolitan University; Vector Institute","funders":"","keywords":"Padding; Encoding (memory); Heuristics; Position (finance); Computer science; Convolutional neural network; Artificial intelligence; Boundary (topology); ENCODE; Filter (signal processing); Pattern recognition (psychology); Theoretical computer science; Algorithm; Computer vision; Mathematics; Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001173323,0.0009260044,0.000980812,0.0005644186,0.0004626819,0.002313306,0.001708704,0.001576009,0.006337396],"category_scores_gemma":[0.006374087,0.0008817696,0.0006399719,0.00065495,0.001011244,0.00783321,0.001435981,0.00275082,0.0007845998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008991529,"about_ca_system_score_gemma":0.000992598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006979767,"about_ca_topic_score_gemma":0.007043977,"domain_scores_codex":[0.9995965,0.00007558658,0.00002433055,0.0001038623,0.0001322675,0.00006747797],"domain_scores_gemma":[0.9983448,0.0008220288,0.0001605941,0.0003727449,0.0002122474,0.00008775242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007994194,0.0002214036,0.008635396,0.0004974277,0.0001585165,0.0005671327,0.0005029268,0.3561754,0.02898676,0.2453177,0.008757403,0.3493806],"study_design_scores_gemma":[0.00001294634,0.00009975681,0.001346142,0.00006725909,0.00004035251,0.0001004003,0.00006134326,0.8959824,0.00572894,0.09425922,0.002271002,0.00003023514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2087559,0.005724342,0.7590653,0.005836733,0.0007592863,0.00007025235,0.0009186033,0.001679367,0.01719019],"genre_scores_gemma":[0.9224693,0.002153574,0.06293069,0.0006062918,0.0002843869,0.00002784538,0.0004822577,0.0002768372,0.01076881],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006979767,"threshold_uncertainty_score":0.02120072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0060274247605354,"score_gpt":0.2768037056435105,"score_spread":0.2707762808829751,"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."}}