{"id":"W4415377194","doi":"10.1016/j.cviu.2025.104543","title":"XLITE-Unet: Extremely Light and Efficient Deep learning architecture with selective atrous and axial depthwise convolution for image segmentation","year":2025,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Centre National de la Recherche Scientifique; Canadian Nautical Research Society; University of Central Arkansas","keywords":"Deep learning; Benchmark (surveying); Segmentation; Convolution (computer science); Convolutional neural network; Range (aeronautics); Channel (broadcasting); Network architecture","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003493597,0.0009760537,0.0004691851,0.0004745021,0.0003003645,0.0007397371,0.002001361,0.0008990878,0.008235537],"category_scores_gemma":[0.0008071013,0.0004329727,0.0004904306,0.0004150429,0.000309856,0.0009774598,0.001349995,0.001825053,0.002505017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000778528,"about_ca_system_score_gemma":0.001253774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005321468,"about_ca_topic_score_gemma":0.01642954,"domain_scores_codex":[0.9998343,0.00001711195,0.000007318532,0.00004435506,0.0000652547,0.00003170055],"domain_scores_gemma":[0.9998184,0.00004260081,0.00001372725,0.00004053059,0.00005816386,0.00002669015],"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":[0.000597589,0.0002955632,0.001373203,0.0003457013,0.0002228593,0.0002072578,0.00009872342,0.0901022,0.05353919,0.01917723,0.07360828,0.7604321],"study_design_scores_gemma":[0.00004513121,0.0001370929,0.0002910706,0.0000264447,0.00002676301,0.00009023398,0.00001592369,0.9546384,0.02677286,0.006177198,0.01175775,0.0000210762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02294168,0.0007659413,0.9468818,0.0003720988,0.0002388446,0.0001077788,0.001339737,0.02108063,0.006271495],"genre_scores_gemma":[0.19916,0.0004363379,0.771332,0.000791967,0.0000744531,0.0002442457,0.004589434,0.001420062,0.02195157],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008235537,"threshold_uncertainty_score":0.02755064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009156559389302646,"score_gpt":0.2545318479845313,"score_spread":0.2453752885952287,"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."}}