{"id":"W4416922229","doi":"10.1109/access.2025.3639410","title":"DSConvNet: A Lightweight Architecture for Extracting Image Features From Depthwise Separable Convolution Network for Edge Devices","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Convolution (computer science); Benchmark (surveying); Convolutional neural network; Block (permutation group theory); Image (mathematics); Feature (linguistics); Separable space; Enhanced Data Rates for GSM Evolution; Object (grammar)","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":[0.0002431976,0.001030114,0.0004660635,0.0006377593,0.0002786251,0.0006561299,0.001940348,0.0005342413,0.004380109],"category_scores_gemma":[0.0005921524,0.0003846198,0.0004904993,0.0005560022,0.0002881264,0.001458817,0.0009459899,0.0009219764,0.001656661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000680966,"about_ca_system_score_gemma":0.0008136825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005115076,"about_ca_topic_score_gemma":0.01296746,"domain_scores_codex":[0.9998472,0.00001179087,0.000008194917,0.00004422043,0.00005621984,0.000032325],"domain_scores_gemma":[0.9998752,0.00002473467,0.00001366815,0.00002930966,0.00004401349,0.00001308208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005734734,0.0002126462,0.002632085,0.0002835013,0.0001821974,0.0002522873,0.00008355579,0.1155026,0.06870248,0.01274528,0.03283668,0.7659932],"study_design_scores_gemma":[0.00002419969,0.0001558403,0.0007882611,0.00002757244,0.00003843056,0.000170576,0.00001954428,0.9381837,0.042231,0.005187359,0.01314575,0.00002779021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05761982,0.001297596,0.9187834,0.0002238755,0.000291375,0.0001753813,0.001214327,0.0114934,0.00890078],"genre_scores_gemma":[0.4653539,0.000946281,0.498503,0.0006265978,0.0000679439,0.0002921817,0.00684219,0.0006396929,0.02672821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005115076,"threshold_uncertainty_score":0.01465291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0218541881762299,"score_gpt":0.3318302541726655,"score_spread":0.3099760659964356,"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."}}