{"id":"W2798419898","doi":"10.1109/cvprw.2018.00032","title":"Semantic Binary Segmentation Using Convolutional Networks without Decoders","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund; Nvidia","keywords":"Segmentation; Computer science; Encoder; Artificial intelligence; Convolutional neural network; Computation; Pattern recognition (psychology); Scale-space segmentation; Binary number; Image segmentation; Encoding (memory); Feature (linguistics); Computer vision; Algorithm; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004240349,0.001594768,0.0006908212,0.00100139,0.0004030906,0.001310455,0.001522004,0.001299152,0.005014075],"category_scores_gemma":[0.001235441,0.0007472037,0.0008388294,0.001013417,0.0008088713,0.002960362,0.001207332,0.001373305,0.002913745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00134839,"about_ca_system_score_gemma":0.0013371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007409724,"about_ca_topic_score_gemma":0.01308983,"domain_scores_codex":[0.9996643,0.00003446152,0.00001524783,0.00014448,0.0000837412,0.00005769754],"domain_scores_gemma":[0.999689,0.0000836494,0.00003502878,0.0001068229,0.00006250758,0.00002297756],"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":[0.0005581671,0.0001762811,0.001343373,0.0003013104,0.0001479484,0.0001735807,0.0001211597,0.3794537,0.05277064,0.0411575,0.01026736,0.513529],"study_design_scores_gemma":[0.000013175,0.000042979,0.000265409,0.00001682624,0.00002243374,0.00005999688,0.00001513651,0.9579105,0.01930026,0.01804426,0.004297083,0.00001197642],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04200011,0.0007696712,0.9360033,0.0003272491,0.0001154429,0.00008831391,0.0008365976,0.01043911,0.009420272],"genre_scores_gemma":[0.5240102,0.0006775371,0.4539724,0.000391172,0.00007099897,0.0001333169,0.003839907,0.0009472554,0.01595708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007409724,"threshold_uncertainty_score":0.0167737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04271934472222172,"score_gpt":0.3196910141322704,"score_spread":0.2769716694100487,"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."}}