{"id":"W3102296895","doi":"","title":"Texture classification in extreme scale variations using GANet","year":2019,"lang":"en","type":"article","venue":"University of Oulu Repository (University of Oulu)","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":29,"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); Artificial intelligence; Computer science; Scale (ratio); Texture (cosmology); Image texture; Image segmentation; Computer vision; Segmentation; Image (mathematics); Geography; Cartography","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":[0.0001836866,0.0001116679,0.000233722,0.000230651,0.000194492,0.00001782487,0.0008909377,0.0001631901,0.00006924146],"category_scores_gemma":[0.000009503523,0.000155741,0.0001160789,0.0006426302,0.0001529392,0.0008443563,0.0002096284,0.0001635467,0.00001797481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001920113,"about_ca_system_score_gemma":0.0001725883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007463793,"about_ca_topic_score_gemma":0.00003308025,"domain_scores_codex":[0.9989313,0.0001137287,0.000144379,0.0003619963,0.0002886674,0.0001599562],"domain_scores_gemma":[0.9987167,0.0000664793,0.0003389992,0.000562132,0.0002471349,0.00006855186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002405248,0.001036693,0.1181086,0.0003172622,0.0001411557,0.0002083042,0.01257106,0.0002912946,0.8161035,0.03558481,0.001148731,0.01424809],"study_design_scores_gemma":[0.002232447,0.0002894521,0.6656238,0.0002786098,0.000124055,0.00007919446,0.01206388,0.2935885,0.01594707,0.0008038049,0.008178846,0.0007903117],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4051728,0.00005382806,0.5750386,0.0005211085,0.0001908692,0.0003482472,0.00001117876,0.0001531193,0.01851025],"genre_scores_gemma":[0.9626104,0.00002358213,0.03236524,0.00000710936,0.000008631774,1.575329e-8,0.000004640992,0.000004509255,0.004975892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8001564,"threshold_uncertainty_score":0.6350935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03319248725837515,"score_gpt":0.1963742119322543,"score_spread":0.1631817246738791,"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."}}