{"id":"W4409923782","doi":"10.1007/s10044-025-01474-1","title":"Enhancing out-of-distribution learning in computer vision through dominant feature masking","year":2025,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Masking (illustration); Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Computer science; Distribution (mathematics); Computer vision; Mathematics; Art; Visual arts","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":[0.0002888141,0.00009454261,0.000218143,0.0001961279,0.0001704127,0.0001096449,0.0002044229,0.00005143495,0.000006828408],"category_scores_gemma":[0.00001038389,0.00008978311,0.00008803055,0.001344198,0.00002781378,0.000163009,0.0001319065,0.0001692512,0.000005473002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000304051,"about_ca_system_score_gemma":0.00001816603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007031079,"about_ca_topic_score_gemma":0.0001962323,"domain_scores_codex":[0.999062,0.00007445631,0.0002676999,0.0003324569,0.0001226273,0.0001407655],"domain_scores_gemma":[0.9994364,0.00009099152,0.0001431949,0.0002421652,0.00005990101,0.00002734609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004023665,0.0001176195,0.04365905,0.00007023333,0.0002066925,0.000002730628,0.001871646,0.01693538,0.005494055,0.02141122,0.00009526213,0.9101321],"study_design_scores_gemma":[0.0004454479,0.00003144994,0.1421734,0.0001172623,0.0001571608,0.000001016293,0.0002363599,0.8307192,0.002834437,0.001257066,0.02179576,0.0002314508],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004793698,0.0001342911,0.9938107,0.0007854989,0.00003310632,0.0001202342,0.000002337812,0.00003518486,0.0002849296],"genre_scores_gemma":[0.9855886,0.00005893441,0.01389157,0.000168858,0.00002289235,0.00003464818,0.00005286995,0.000002900475,0.0001787201],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9807949,"threshold_uncertainty_score":0.3661249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009145509653189155,"score_gpt":0.2835948923947317,"score_spread":0.2744493827415425,"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."}}