{"id":"W4413385029","doi":"10.1016/j.cviu.2025.104482","title":"EntroFormer: An entropy-based sparse vision transformer for real-time semantic segmentation","year":2025,"lang":"en","type":"article","venue":"Computer Vision and Image Understanding","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Artificial intelligence; Segmentation; Computer science; Computer vision; Transformer; Pattern recognition (psychology); Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002151143,0.0002183866,0.000225832,0.0002484961,0.0005299339,0.0004204467,0.0003375465,0.00006049573,0.000009643189],"category_scores_gemma":[0.000005093829,0.0001977535,0.00008578574,0.0004131485,0.00008276868,0.001214067,0.00007298464,0.00009133303,0.000009064447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001795918,"about_ca_system_score_gemma":0.00004374288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000237914,"about_ca_topic_score_gemma":0.000002269326,"domain_scores_codex":[0.9984874,0.00006010982,0.000325058,0.000596364,0.0001842767,0.0003468125],"domain_scores_gemma":[0.9990714,0.0002548785,0.00009985047,0.0003815869,0.00006454111,0.0001277205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002517675,0.0004227212,0.0001030298,0.0002480142,0.00005698206,0.00001102088,0.0007197139,0.002253497,0.4389904,0.3426364,0.009401243,0.2049052],"study_design_scores_gemma":[0.001590404,0.0003888805,0.0001648011,0.0001170384,0.00002243616,0.000004503357,0.00005053,0.9657382,0.006797203,0.02369445,0.001201585,0.0002299024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004806723,0.00002878659,0.9918359,0.001846611,0.0002181559,0.0007759881,0.000005080471,0.0002451384,0.000237618],"genre_scores_gemma":[0.3577451,0.00013199,0.6407393,0.001011423,0.00008773815,0.00004863931,0.00006586681,0.00002282326,0.0001472029],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9634848,"threshold_uncertainty_score":0.8064156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02455806570169888,"score_gpt":0.3132847889971822,"score_spread":0.2887267232954833,"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."}}