{"id":"W4312602363","doi":"10.1109/cvpr52688.2022.00129","title":"GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Huawei Technologies; Compute Canada; Automotive Research Center","keywords":"Computer science; Artificial intelligence; Robustness (evolution); Segmentation; Code (set theory); Image (mathematics); Unsupervised learning; Computer vision; Pattern recognition (psychology); Image segmentation; Artificial neural network; Set (abstract data type)","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005349392,0.0003434849,0.0003452433,0.0002377795,0.0008818877,0.0007330769,0.0005205447,0.0000686335,0.001513569],"category_scores_gemma":[0.00001433509,0.0003366155,0.0001073822,0.0003725805,0.00004507062,0.0004338252,0.0005122558,0.0005637604,0.0001824584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007621665,"about_ca_system_score_gemma":0.00005413499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003268447,"about_ca_topic_score_gemma":0.000008568589,"domain_scores_codex":[0.9966016,0.0009047272,0.000426284,0.001004019,0.000643487,0.0004198637],"domain_scores_gemma":[0.9988883,0.0001397942,0.0001368975,0.0003648362,0.0001714312,0.0002987414],"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":[0.00004672541,0.0002310015,0.00006960361,0.00001216666,0.00003027347,0.00003365483,0.001013318,0.002062674,0.04036746,0.00006153762,0.03557626,0.9204953],"study_design_scores_gemma":[0.0009810686,0.00181775,0.0003400307,0.00005518332,0.00001369446,0.00003079632,0.0001047251,0.9768371,0.006963056,0.0002648543,0.01198727,0.0006044931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09235118,0.00002874934,0.9016523,0.003743414,0.00116783,0.0004263119,0.00006824591,0.0001421759,0.0004197239],"genre_scores_gemma":[0.96941,0.00009101624,0.01884606,0.01034013,0.0005087088,0.0001701684,0.0002885664,0.00003341846,0.0003119106],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9747744,"threshold_uncertainty_score":0.9999086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03295431514156284,"score_gpt":0.2556871973389931,"score_spread":0.2227328821974303,"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."}}