{"id":"W4412601528","doi":"10.2139/ssrn.5363643","title":"Lightweight Deep Learning for Visual Perception: A Survey of Models, Compression Strategies, and Edge Deployment Challenges","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Software deployment; Perception; Deep learning; Enhanced Data Rates for GSM Evolution; Computer science; Artificial intelligence; Computer vision; Human–computer interaction; Psychology; Software engineering; Neuroscience","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001303588,0.0003063917,0.0004392412,0.0001757628,0.0003396443,0.0001633394,0.0009280329,0.0002137508,0.000001264445],"category_scores_gemma":[0.00002440534,0.0002822535,0.0001188053,0.0001723657,0.00005368241,0.0004496761,0.0008158222,0.002507855,5.682907e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004574554,"about_ca_system_score_gemma":0.001875657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005084676,"about_ca_topic_score_gemma":0.0008862892,"domain_scores_codex":[0.9971051,0.000306371,0.0005045838,0.0006273173,0.0002914794,0.001165101],"domain_scores_gemma":[0.9983891,0.0002878462,0.0005092835,0.0003739823,0.0003445004,0.0000952582],"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":[0.0000877807,0.0001707129,0.00009880403,0.0001747014,0.000206671,8.177963e-7,0.0008861255,0.1132147,0.0001415171,0.4348344,0.00002770402,0.450156],"study_design_scores_gemma":[0.000482106,0.0003407674,0.002111189,0.0002011414,0.00003733173,0.00005164598,0.0005238557,0.5021735,0.00003145116,0.4934138,0.0003217185,0.0003115035],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01176001,0.03338872,0.9533751,0.0005651873,0.0001971271,0.0004860489,0.000004073822,0.00008010347,0.0001436543],"genre_scores_gemma":[0.9016652,0.08821854,0.009607381,0.00001800487,0.0001585794,0.00009486353,0.00002915449,0.00002186433,0.000186395],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9437677,"threshold_uncertainty_score":0.999963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04220392858090016,"score_gpt":0.3140330745896108,"score_spread":0.2718291460087107,"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."}}