{"id":"W4312674867","doi":"10.1109/lra.2022.3227866","title":"Self-Supervised Feature Learning for Long-Term Metric Visual Localization","year":2022,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Ground truth; Computer science; Computer vision; Feature (linguistics); Metric (unit); Pattern recognition (psychology); Visualization; Pipeline (software); Artificial neural network; Matching (statistics); Estimator; 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":[0.000147266,0.0001633952,0.0001628048,0.000260464,0.000394565,0.0001103342,0.00007437401,0.00006077455,0.00001364942],"category_scores_gemma":[0.00001546114,0.0001866297,0.00005672337,0.0004435036,0.00001345115,0.0001289282,0.00001792415,0.000171203,0.000002722202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000124494,"about_ca_system_score_gemma":0.00001121823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001273966,"about_ca_topic_score_gemma":8.98307e-7,"domain_scores_codex":[0.9990811,0.00005516617,0.0002170993,0.0001924181,0.0002347955,0.0002194552],"domain_scores_gemma":[0.999669,0.00007088111,0.00006093486,0.00009133801,0.00004624944,0.00006158006],"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":[0.000004380537,0.0000241117,0.001917754,0.0001753086,0.00003928609,0.00000312251,0.0001940132,0.9918389,0.002226408,0.000164979,0.001140562,0.002271149],"study_design_scores_gemma":[0.0005333415,0.00006420474,0.001694907,0.00001103111,0.00005110493,0.000007545217,0.0000307983,0.9961861,0.0004747405,0.00001068646,0.0007087598,0.0002268236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08873319,0.0001319185,0.9090659,0.000641772,0.0005729879,0.0003401532,0.000004859201,0.0004896342,0.00001960319],"genre_scores_gemma":[0.9902368,0.00005709442,0.008539481,0.000580948,0.0001380445,0.00004566269,0.0002977235,0.00006317069,0.00004104965],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9015036,"threshold_uncertainty_score":0.7610539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00783108971355151,"score_gpt":0.2190876393370023,"score_spread":0.2112565496234508,"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."}}