{"id":"W4394597746","doi":"10.1109/wacv57701.2024.00332","title":"SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labelling","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Object (grammar); Computer science; Object detection; Computer vision; Domain adaptation; Domain (mathematical analysis); Artificial intelligence; Labelling; Adaptation (eye); Pattern recognition (psychology); Mathematics; Optics; Physics","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":[0.0003189779,0.000197408,0.0001366282,0.0002211375,0.0005277032,0.0004456287,0.0002704168,0.00009267847,0.000008314365],"category_scores_gemma":[0.00004782635,0.0001979055,0.0000936997,0.0009933471,0.00004779306,0.001551075,0.00006258717,0.0001513046,0.00004490158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002262993,"about_ca_system_score_gemma":0.0001143787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002609445,"about_ca_topic_score_gemma":0.00003956502,"domain_scores_codex":[0.9982295,0.00005824413,0.0004036624,0.0006824053,0.0002936693,0.0003324947],"domain_scores_gemma":[0.9986796,0.0005546649,0.0001251066,0.0003608836,0.0002091259,0.00007058458],"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":[0.00004759411,0.00005682198,0.00008755032,0.0001249726,0.00005139056,0.00000972006,0.001381851,0.494529,0.09384239,0.05814922,0.00005153109,0.3516679],"study_design_scores_gemma":[0.0002160099,0.00006412408,0.0001822336,0.00003886691,0.00001189701,0.0000377128,0.00006192041,0.9472064,0.01258988,0.03793915,0.001424692,0.0002271169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06462187,0.0002237885,0.9325896,0.0002029494,0.000627798,0.0007863384,0.00001056433,0.0007768253,0.0001602818],"genre_scores_gemma":[0.3848995,0.00002282496,0.6142855,0.00009401476,0.0002188249,0.0001426723,0.000022859,0.00002631872,0.0002875137],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4526774,"threshold_uncertainty_score":0.807035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0400239221683896,"score_gpt":0.3196846485735745,"score_spread":0.2796607264051849,"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."}}