{"id":"W4382458079","doi":"10.1609/aaai.v37i1.25193","title":"Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Segmentation; Domain (mathematical analysis); Task (project management); Context (archaeology); Generalization; Artificial intelligence; Domain adaptation; Class (philosophy); Adaptation (eye); Code (set theory); Pattern recognition (psychology); Machine learning; Mathematics; Geography","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":[0.0009046596,0.0001931786,0.0002056214,0.0002448945,0.0003775864,0.0002326745,0.001014575,0.00007551088,0.00004291149],"category_scores_gemma":[0.0002546035,0.00015896,0.0001450648,0.00119337,0.0001713201,0.0004141562,0.0001937509,0.0001884174,0.0001979529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006268113,"about_ca_system_score_gemma":0.00008772327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000133771,"about_ca_topic_score_gemma":0.000008537844,"domain_scores_codex":[0.9981382,0.00003039775,0.0004627114,0.0004814164,0.0005291012,0.0003581216],"domain_scores_gemma":[0.9986423,0.0002304266,0.000348755,0.0001800759,0.0005172574,0.00008121217],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007917496,0.0000569456,0.00007078966,0.00002638513,0.00002269512,3.93676e-7,0.002661546,0.000269289,0.05889757,0.8969029,0.0004572803,0.04055502],"study_design_scores_gemma":[0.00009791316,0.000286497,0.0004804725,0.0001371757,0.00001172132,0.000004851207,0.00415318,0.1864062,0.1721873,0.6351183,0.0008305462,0.000285734],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1327012,0.00001743607,0.8462805,0.00842205,0.001247898,0.001240342,0.00001467386,0.0004418868,0.00963404],"genre_scores_gemma":[0.9652485,0.00001355965,0.03362539,0.000225804,0.00009031089,0.0001243213,0.000002787891,0.00001613053,0.0006532073],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8325472,"threshold_uncertainty_score":0.6482202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1005609645804683,"score_gpt":0.3156389768482556,"score_spread":0.2150780122677873,"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."}}