{"id":"W7116867560","doi":"10.21203/rs.3.rs-7339928/v1","title":"Lite-FARNet: A Light-weight Feedback Attention Residual Network for Efficient Multi-Class Segmentation in Complex Urban Scenes","year":2025,"lang":"","type":"preprint","venue":"Research Square","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Henan Provincial Science and Technology Research Project","keywords":"Segmentation; Software deployment; Inference; Adaptability; Context (archaeology); Residual; Key (lock); Representation (politics); Feature (linguistics)","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":[0.000899596,0.001764759,0.001436893,0.00117117,0.0005923725,0.001067553,0.003608863,0.002401994,0.007456217],"category_scores_gemma":[0.001422927,0.0008260384,0.0008831582,0.0008336973,0.0005438811,0.001620357,0.001524681,0.001878004,0.002701195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00108075,"about_ca_system_score_gemma":0.00152981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02459756,"about_ca_topic_score_gemma":0.04795044,"domain_scores_codex":[0.9996361,0.0000519307,0.00001167266,0.0001531262,0.00007445308,0.00007275988],"domain_scores_gemma":[0.9996197,0.0001187272,0.00002865124,0.00007683003,0.0001138515,0.00004231913],"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":[0.0006196107,0.0003120799,0.0007341475,0.0002226293,0.0002145772,0.0001230747,0.000108308,0.1715253,0.03013657,0.00501521,0.02546208,0.7655263],"study_design_scores_gemma":[0.0000229543,0.000046293,0.0001795617,0.00001071402,0.00002046934,0.00002208782,0.00001264188,0.9897557,0.006157987,0.001886848,0.001872279,0.00001248593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03522826,0.0009125898,0.9418222,0.000386329,0.0002039641,0.0001409233,0.0009510433,0.01686396,0.003490689],"genre_scores_gemma":[0.2929492,0.0004403498,0.6826425,0.0007315656,0.0001457674,0.000202472,0.004147084,0.001697492,0.01704358],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02459756,"threshold_uncertainty_score":0.04890877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1006398905420324,"score_gpt":0.4087886899744186,"score_spread":0.3081487994323862,"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."}}