{"id":"W4389668005","doi":"10.1109/iros55552.2023.10342415","title":"What to Learn: Features, Image Transformations, or Both?","year":2023,"lang":"en","type":"article","venue":"","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Rehabilitation Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Computer science; Feature (linguistics); Transformation (genetics); Computer vision; Image (mathematics); Pattern recognition (psychology); Transfer of learning; Artificial neural network; Feature extraction; Matching (statistics); Robustness (evolution); Invariant (physics); Term (time); Robotics; Machine learning; Robot; Mathematics","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":[0.00005422988,0.00007397069,0.00006975033,0.0001057931,0.00004395729,0.0001429201,0.00005659952,0.00004217538,0.0002189996],"category_scores_gemma":[0.00001057936,0.00006031692,0.00002486035,0.0003966114,0.000004710274,0.0002973445,0.000005156412,0.00005600462,0.0007172203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002067676,"about_ca_system_score_gemma":0.000006571121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007937757,"about_ca_topic_score_gemma":0.00006821212,"domain_scores_codex":[0.9995581,0.000006650766,0.0001090949,0.00007034319,0.0001003052,0.0001555405],"domain_scores_gemma":[0.9997849,0.00002087196,0.000003592131,0.0001088608,0.00001736071,0.00006436633],"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":[0.000006906711,0.000005559184,0.000005047857,0.00005452317,0.0000119081,0.000009127216,0.000630652,0.8077829,0.002531434,0.001620049,0.1759119,0.01142999],"study_design_scores_gemma":[0.0004356372,0.00006327929,0.001301013,0.00006730788,0.00001387838,0.000008884167,0.001680671,0.8015364,0.01378379,0.0002199636,0.1804854,0.0004038323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02541443,0.0003075365,0.9184932,0.008774973,0.002441723,0.0008951545,0.00002641851,0.004477793,0.03916877],"genre_scores_gemma":[0.8910903,0.004194967,0.0238233,0.002886444,0.0004637994,0.00008871433,0.000732075,0.0002478482,0.07647257],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8946699,"threshold_uncertainty_score":0.9218655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01268046564759954,"score_gpt":0.2390988775793706,"score_spread":0.226418411931771,"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."}}