{"id":"W4285274933","doi":"10.1109/lgrs.2022.3185118","title":"PolSAR Image Classification Based on Deep Convolutional Neural Networks Using Wavelet Transformation","year":2022,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Synthetic Aperture Radar (SAR) Applications and Techniques","field":"Engineering","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Centre For Cold Ocean Resources Engineering; Memorial University of Newfoundland","funders":"Science and Engineering Research Council","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Contextual image classification; Feature extraction; Deep learning; Synthetic aperture radar; Transformation (genetics); Wavelet transform; Wavelet; Feature (linguistics); Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000304846,0.0006218455,0.0003246165,0.0005725826,0.000158154,0.0004611179,0.0004989645,0.0003173457,0.001595209],"category_scores_gemma":[0.0005123207,0.0002699333,0.0004660182,0.0006210364,0.0002264497,0.0008333728,0.0004521518,0.0006362403,0.000627402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004758039,"about_ca_system_score_gemma":0.0004674396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006849219,"about_ca_topic_score_gemma":0.0095119,"domain_scores_codex":[0.9998692,0.00001203071,0.000007700484,0.00003779886,0.000044753,0.00002850768],"domain_scores_gemma":[0.9998289,0.00003888251,0.00002678447,0.00003264016,0.00006143843,0.00001128897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001826224,0.0001634394,0.003792374,0.0000882258,0.0001295692,0.000126805,0.00005908396,0.2891586,0.08253165,0.00501028,0.005367117,0.6133903],"study_design_scores_gemma":[0.000003147107,0.00001786627,0.0007779328,0.000003723805,0.000009906196,0.00001947591,0.00000569032,0.9891647,0.008450665,0.0008077087,0.0007342582,0.000004968083],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09483575,0.0003685197,0.8976474,0.0001938119,0.00007236423,0.00005544667,0.0002870869,0.002927841,0.003611729],"genre_scores_gemma":[0.6970618,0.0005363869,0.2922892,0.0001831451,0.00004859671,0.00008090192,0.00174602,0.0001606469,0.007893266],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006849219,"threshold_uncertainty_score":0.01361871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01258089146574382,"score_gpt":0.2179484790794425,"score_spread":0.2053675876136987,"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."}}