{"id":"W4313184971","doi":"10.1109/cvpr52688.2022.01642","title":"MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea","keywords":"Computer science; Modal; Modality (human–computer interaction); Segmentation; Adaptation (eye); Modalities; Domain adaptation; Consistency (knowledge bases); Test data; Scheme (mathematics); Artificial intelligence; Pattern recognition (psychology); Machine learning; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007066616,0.0003550216,0.0003575646,0.000388109,0.0008554899,0.000599466,0.0004742187,0.00008946349,0.0007614257],"category_scores_gemma":[0.00003913018,0.0003731973,0.000131338,0.0003624793,0.00005199311,0.000680855,0.0002565818,0.0004018639,0.0002803986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009448388,"about_ca_system_score_gemma":0.00009526887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002432139,"about_ca_topic_score_gemma":0.00001258628,"domain_scores_codex":[0.9969879,0.0004148483,0.0005624046,0.0009563721,0.0006676389,0.0004108366],"domain_scores_gemma":[0.9982539,0.0005540886,0.000371524,0.0003548468,0.0002703847,0.0001952065],"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":[0.00007801777,0.0003463928,0.00009727986,0.00005478244,0.000025227,0.00001867874,0.001847667,0.001328859,0.004373353,0.0002461239,0.001768106,0.9898155],"study_design_scores_gemma":[0.002472786,0.001399805,0.001625457,0.00008314742,0.00002204901,0.00004813668,0.0002919764,0.9902536,0.000542802,0.0006651985,0.002093706,0.0005012938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02225344,0.00001890206,0.9728618,0.002109572,0.001224823,0.0008673975,0.0001301459,0.0002885771,0.00024536],"genre_scores_gemma":[0.8692679,0.00007389791,0.1210693,0.007090164,0.0002647409,0.0004508442,0.0006613858,0.00005499879,0.001066818],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9893142,"threshold_uncertainty_score":0.999872,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0619686168823289,"score_gpt":0.2893112902145141,"score_spread":0.2273426733321852,"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."}}