{"id":"W4412445034","doi":"10.1109/taes.2025.3589337","title":"IRASNet: Improved Feature-Level Clutter Reduction for Domain Generalized SAR-ATR","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Aerospace and Electronic Systems","topic":"Advanced SAR Imaging Techniques","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nexen (Canada)","funders":"Defense Acquisition Program Administration; Korea Research Institute for Defense Technology Planning and Advancement","keywords":"Clutter; Reduction (mathematics); Computer science; Feature (linguistics); Artificial intelligence; Synthetic aperture radar; Radar tracker; Radar signal processing; Radar; Remote sensing; Pattern recognition (psychology); Signal processing; Mathematics; Telecommunications; Geology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001628701,0.0002572485,0.0002822908,0.0001705264,0.0001909025,0.00007068937,0.0001044846,0.0001706643,0.000002576175],"category_scores_gemma":[0.000001852426,0.0002604882,0.0001007889,0.0002335023,0.00003810346,0.0001229886,8.677909e-7,0.00034212,0.000002747966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003808655,"about_ca_system_score_gemma":0.0000446966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005631609,"about_ca_topic_score_gemma":0.00007650741,"domain_scores_codex":[0.9988605,0.00003247166,0.0002085069,0.0003132905,0.00008860191,0.0004966516],"domain_scores_gemma":[0.9995275,0.00003845392,0.00003685739,0.0003003477,0.00004563919,0.00005124304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002954814,0.00009008395,0.000008589238,0.0005860516,0.0005161379,0.000001154888,0.0003806895,0.04096582,0.9066408,0.002347178,0.02961521,0.01855281],"study_design_scores_gemma":[0.005438876,0.000624249,0.00003771417,0.0005478321,0.0003269855,0.0001476313,0.0005475272,0.1472146,0.6676073,0.003911365,0.1720449,0.001550983],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01546309,0.001785978,0.9791116,0.0007449163,0.001087568,0.0009319168,0.00003554752,0.0006953552,0.0001440803],"genre_scores_gemma":[0.9830053,0.0005515891,0.01018336,0.00008184927,0.0001157315,0.0004696101,0.000007055651,0.00006908507,0.005516391],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9689282,"threshold_uncertainty_score":0.9999847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008955744797225735,"score_gpt":0.2428431013356562,"score_spread":0.2338873565384305,"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."}}