{"id":"W4312882064","doi":"10.1109/lgrs.2022.3227164","title":"Cross-Domain Few-Shot Contrastive Learning for Hyperspectral Images Classification","year":2022,"lang":"en","type":"article","venue":"IEEE Geoscience and Remote Sensing Letters","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Artificial intelligence; Discriminative model; Computer science; Pattern recognition (psychology); Hyperspectral imaging; Feature extraction; Deep learning; Residual; Support vector machine; Contextual image classification; Feature learning; Convolutional neural network; Similarity (geometry); Class (philosophy); Feature (linguistics); Machine learning; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005405948,0.0002019734,0.0001910444,0.000174807,0.0009596883,0.0002348925,0.0001380554,0.0000480666,0.000003157726],"category_scores_gemma":[0.0000977577,0.0002199923,0.00007289249,0.0003309496,0.0003931686,0.0002375652,0.00002638018,0.000375314,0.000004616457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00024615,"about_ca_system_score_gemma":0.00002938959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004803001,"about_ca_topic_score_gemma":0.000003455067,"domain_scores_codex":[0.9984081,0.00008406219,0.000254276,0.0004728516,0.0002951794,0.0004855154],"domain_scores_gemma":[0.9993716,0.0001648721,0.00009377731,0.0002143991,0.00006778132,0.00008760026],"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":[0.00001807444,0.000004256821,0.00004207089,0.00001852868,0.00001010179,0.00001207715,0.0006373523,0.0151473,0.9310429,0.000009708444,0.0004901434,0.05256753],"study_design_scores_gemma":[0.0005364519,0.00006749712,0.009394634,0.00002784256,0.00002168838,0.0001941422,0.001087929,0.9568342,0.02669782,0.000149259,0.00457469,0.0004138499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6496525,0.0000544809,0.3470745,0.001618854,0.0008446616,0.000239931,0.000007068894,0.000232961,0.0002750716],"genre_scores_gemma":[0.9533246,0.00002270655,0.04558769,0.0005154781,0.0001856936,7.585612e-7,0.00001708572,0.00004605756,0.0002999901],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9416869,"threshold_uncertainty_score":0.8971028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02190387402947406,"score_gpt":0.256930765598226,"score_spread":0.2350268915687519,"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."}}