{"id":"W4406857259","doi":"10.1109/access.2025.3534444","title":"Hierarchical Feature Attention Learning Network for Detecting Object and Discriminative Parts in Fine-Grained Visual Classification","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Korea Institute of Marine Science and Technology promotion; Hankuk University of Foreign Studies","keywords":"Discriminative model; Computer science; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Object (grammar); Object detection; Feature learning; Feature extraction; Visual attention; Contextual image classification; Machine learning; Computer vision; 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":[0.0003836429,0.0001228844,0.0001811947,0.0001743983,0.0001725815,0.0001416673,0.0000655332,0.0001754399,0.000001097524],"category_scores_gemma":[0.0001756557,0.0001177131,0.00004791068,0.0004349714,0.00001599951,0.0002153706,0.0000197368,0.0003450265,8.037055e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007147591,"about_ca_system_score_gemma":0.0000131964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003420698,"about_ca_topic_score_gemma":0.0002155957,"domain_scores_codex":[0.9991811,0.00008813295,0.0002224485,0.0002110703,0.00008400517,0.0002132493],"domain_scores_gemma":[0.9995683,0.000234015,0.00005254005,0.00007113894,0.00004478895,0.0000292192],"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":[0.0006318531,0.00007542732,0.07624971,0.0008230794,0.0001733621,0.000009554364,0.001118651,0.1346178,0.04854508,0.001089469,0.005243728,0.7314223],"study_design_scores_gemma":[0.002540104,0.0002315164,0.2211759,0.000877185,0.00006367644,0.000006759059,0.000605469,0.7579311,0.01051005,0.001618107,0.003941656,0.000498402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9071269,0.0001329985,0.09034583,0.00009352403,0.001172095,0.0005199279,0.000001980896,0.0001545645,0.000452173],"genre_scores_gemma":[0.9991788,0.000008442469,0.00009455662,0.00001146038,0.0003622865,0.0001383542,0.000009903111,0.00001643817,0.0001797642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7309239,"threshold_uncertainty_score":0.48002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03249424113555014,"score_gpt":0.3241110343227541,"score_spread":0.2916167931872039,"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."}}