{"id":"W4285249872","doi":"10.1109/lcomm.2022.3182691","title":"Few-Shot Learning UAV Recognition Methods Based on the Tri-Residual Semantic Network","year":2022,"lang":"en","type":"article","venue":"IEEE Communications Letters","topic":"Advanced Measurement and Detection Methods","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Residual; Benchmark (surveying); Artificial intelligence; Noise (video); Feature (linguistics); Shot (pellet); Interference (communication); Feature extraction; Machine learning; Deep learning; Pattern recognition (psychology); Speech recognition; Channel (broadcasting); Telecommunications; Image (mathematics); Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.002138638,0.0001433678,0.0001375109,0.0001211327,0.00120344,0.00003939513,0.0005793414,0.00003023833,0.0001750953],"category_scores_gemma":[0.0001489225,0.0001379551,0.0000858411,0.0005701134,0.00006429428,0.0000694693,0.0000747252,0.0009647107,0.00002735993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000148032,"about_ca_system_score_gemma":0.00001290524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005883765,"about_ca_topic_score_gemma":0.000006022462,"domain_scores_codex":[0.9971651,0.00198247,0.0002459325,0.0001433426,0.0002289227,0.000234253],"domain_scores_gemma":[0.9972216,0.001612978,0.00007451326,0.001023154,0.00003131444,0.00003643929],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001635742,0.00002120398,0.00005462148,0.00000687168,0.00003049714,5.726905e-7,0.0001383648,0.9322569,0.03447222,0.0000496305,0.005856625,0.02709607],"study_design_scores_gemma":[0.0008065754,0.0001314936,0.0004231894,0.00006135958,0.0001210278,0.000009535855,0.0005293789,0.7423359,0.01751986,0.001221488,0.2362006,0.0006396361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01609864,0.0004815119,0.9645292,0.009760131,0.001207661,0.0005293762,0.000008379665,0.0007964046,0.006588745],"genre_scores_gemma":[0.7251454,0.00009767686,0.268743,0.004820913,0.0002362882,0.0007120123,0.00006923483,0.00008090814,0.00009455933],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7090467,"threshold_uncertainty_score":0.9256008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1305772338574004,"score_gpt":0.3373310623014214,"score_spread":0.206753828444021,"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."}}