{"id":"W2994626047","doi":"10.1109/tip.2019.2903300","title":"Texture Classification in Extreme Scale Variations Using GANet","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Tekes; Academy of Finland; Infotech Oulu; National Natural Science Foundation of China","keywords":"Pattern recognition (psychology); Texture (cosmology); Texture filtering; Image texture; Convolutional neural network; Scale (ratio); Pooling; Texture compression","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000215198,0.0001702809,0.0001725941,0.0001919803,0.0002499802,0.0003333507,0.0003297126,0.0000885954,0.0000929025],"category_scores_gemma":[0.000007646449,0.0001691959,0.00006324737,0.0008152655,0.00003832887,0.00155589,0.000003021227,0.0002562923,0.00007353448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001136924,"about_ca_system_score_gemma":0.0001321441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004071873,"about_ca_topic_score_gemma":0.00003551794,"domain_scores_codex":[0.9986572,0.00009545316,0.000274549,0.0004710064,0.0002237642,0.0002780875],"domain_scores_gemma":[0.9992595,0.00008865615,0.0001090349,0.0003622018,0.0001198752,0.00006072087],"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":[0.00002898947,0.0004443313,0.0002163699,0.00007332258,0.00002085701,0.000006969796,0.001839853,0.1500621,0.4599206,0.0001283876,0.00006326765,0.3871949],"study_design_scores_gemma":[0.0003117638,0.00002365824,0.001090216,0.00008410023,0.00001202162,0.00000856065,0.00009290646,0.98095,0.01687381,0.0002560045,0.00009255165,0.0002043921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004697998,0.000049512,0.9930904,0.0004259655,0.0003874483,0.0002280055,0.000004088268,0.00009925481,0.001017357],"genre_scores_gemma":[0.851976,0.000007898523,0.1475191,0.0001445838,0.00004557268,0.000015174,8.646182e-7,0.00001506636,0.000275688],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8472781,"threshold_uncertainty_score":0.6899608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04439003507348081,"score_gpt":0.2556017307662029,"score_spread":0.2112116956927221,"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."}}