{"id":"W4413559141","doi":"10.1109/isie62713.2025.11124764","title":"SS-DeepSeg: An Efficient Deeplab with Smart Scaling for Robust Semantic Segmentation","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Scaling; Segmentation; Artificial intelligence; Natural language processing; Mathematics","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":[0.0006023097,0.00180802,0.001216545,0.001055035,0.000532402,0.001364665,0.003444707,0.001447197,0.007268818],"category_scores_gemma":[0.001364525,0.0007213548,0.00123566,0.00123194,0.0007274085,0.002631339,0.002700502,0.001822163,0.003726349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001267606,"about_ca_system_score_gemma":0.002200479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01035313,"about_ca_topic_score_gemma":0.0209223,"domain_scores_codex":[0.9995674,0.00003757009,0.00001872408,0.0001664453,0.0001304538,0.00007937154],"domain_scores_gemma":[0.9997373,0.0000448759,0.00001706508,0.0000955469,0.0000737361,0.00003146676],"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":[0.0005121267,0.000316442,0.001266393,0.0002679147,0.0002439947,0.0001804241,0.000118393,0.1531274,0.0448599,0.01102296,0.05567451,0.7324095],"study_design_scores_gemma":[0.0000409641,0.00009468586,0.0002978697,0.00001478226,0.00003025179,0.00007655233,0.00003427147,0.963096,0.01792416,0.01033566,0.008029901,0.00002496345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03043995,0.0008819347,0.9154161,0.000391391,0.0001709795,0.0001442026,0.00208884,0.04572911,0.004737418],"genre_scores_gemma":[0.3643605,0.0006050434,0.6050127,0.001142337,0.00009718666,0.0003771029,0.01254202,0.003533604,0.01232964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01035313,"threshold_uncertainty_score":0.02431661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01914798744509053,"score_gpt":0.2818605111163612,"score_spread":0.2627125236712706,"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."}}