{"id":"W4383535470","doi":"10.54254/2755-2721/4/20230430","title":"Fast CNN enhancement using channel attention and residual networks for image super-resolution","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Residual; Computer science; Artificial intelligence; Generalization; Similarity (geometry); Channel (broadcasting); Algorithm; Parametric statistics; Image (mathematics); Reset (finance); Deep learning; Pattern recognition (psychology); Activation function; Process (computing); Artificial neural network; Mathematics; Statistics","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":[0.0001410236,0.0001049025,0.00009166881,0.0001059129,0.0001478553,0.0001108005,0.00009099609,0.00003236821,1.975862e-7],"category_scores_gemma":[0.000008403939,0.0001179802,0.00001365747,0.0002060225,0.00002163292,0.0002689736,0.0001304091,0.00005853013,0.000001023066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002440664,"about_ca_system_score_gemma":0.00001197103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001095925,"about_ca_topic_score_gemma":8.455866e-8,"domain_scores_codex":[0.9993045,0.000003550457,0.0001333633,0.000257097,0.000110832,0.0001906254],"domain_scores_gemma":[0.9997389,0.00006990915,0.00003538507,0.00006776718,0.0000490796,0.00003894045],"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":[0.000008482258,0.00001420563,0.000005755717,0.0001024676,0.00001604075,0.000002285952,0.0001969225,0.8950722,0.04330073,0.04324044,0.00009853315,0.01794192],"study_design_scores_gemma":[0.0001957172,0.00001764153,0.000456566,0.00003035004,0.000003957693,0.000007023997,0.00001338357,0.9874166,0.0004796217,0.01121559,0.00003596946,0.0001275745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01162938,0.00009950878,0.9875341,0.000120348,0.00006196557,0.0001769056,0.000001799814,0.0003622065,0.0000138061],"genre_scores_gemma":[0.427347,0.00001183772,0.5724594,0.00002788585,0.0000596076,0.00004900343,0.00002723137,0.000009876774,0.000008083924],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4157177,"threshold_uncertainty_score":0.4811093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01346383368537359,"score_gpt":0.2479576740988612,"score_spread":0.2344938404134876,"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."}}