Unsupervised domain adaptation (UDA) aims at inferring class labels for unlabeled target domain given a related labeled source dataset. Intuitively, a model trained on source domain normally produces higher uncertainties for unseen data. In this work, we build on this assumption and propose to adapt from source to target domain via calibrating their predictive uncertainties. The uncertainty is quantified as the Renyi entropy, from which we propose a general Renyi entropy regularization (RER) framework. We further employ variational Bayes learning for reliable uncertainty estimation. In addition, calibrating the sample variance of network parameters serves as a plug-in regularizer for training. We discuss the theoretical properties of the proposed method and demonstrate its effectiveness on three domain-adaptation tasks.
Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding
Shanghai AI Laboratory（上海人工智能实验室）；National University of Singapore（新加坡国立大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；The Hong Kong University of Science and Technology（香港科技大学）；S-Lab, Nanyang Technological University（南洋理工大学S-Lab实验室）
Clustering and Uncertainty Analysis to Improve the Machine Learning-based Predictions of SAFARI-1 Control Follower Assembly Axial Neutron Flux Profiles
The South African Nuclear Energy Corporation SOC Ltd (Necsa)（南非核能集团有限公司（Necsa））；North Carolina State University（北卡罗来纳州立大学）
Attentive Continuous Generative Self-training for Unsupervised Domain Adaptive Medical Image Translation
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland School of Dentistry（马里兰大学牙医学院）
