Research interests in the robustness of deep neural networks against domain shifts have been rapidly increasing in recent years. Most existing works, however, focus on improving the accuracy of the model, not the calibration performance which is another important requirement for trustworthy AI systems. Temperature scaling (TS), an accuracy-preserving post-hoc calibration method, has been proven to be effective in in-domain settings, but not in out-of-domain (OOD) due to the difficulty in obtaining a validation set for the unseen domain beforehand. In this paper, we propose consistency-guided temperature scaling (CTS), a new temperature scaling strategy that can significantly enhance the OOD calibration performance by providing mutual supervision among data samples in the source domains. Motivated by our observation that over-confidence stemming from inconsistent sample predictions is the main obstacle to OOD calibration, we propose to guide the scaling process by taking consistencies into account in terms of two different aspects -- style and content -- which are the key components that can well-represent data samples in multi-domain settings. Experimental results demonstrate that our proposed strategy outperforms existing works, achieving superior OOD calibration performance on various datasets. This can be accomplished by employing only the source domains without compromising accuracy, making our scheme directly applicable to various trustworthy AI systems.
Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application
School of Art and Technology, Chung-Ang University(中央大学艺术与技术学院);VIVE STUDIOS(VIVE工作室);GSAIM, Chung-Ang University(中央大学GSAIM);Department of Computer Science and Engineering, Chung-Ang University(中央大学计算机科学与工程系)
Jishou University(吉首大学);Technical University of Munich(慕尼黑技术大学);Renmin University of China(中国人民大学);Northwestern Polytechnical University(西北工业大学);South China Agricultural University(华南农业大学);University of Science and Technology of China(中国科学技术大学);Nanjing University of Aeronautics and Astronautics(南京航空航天大学)
EDUE: Expert Disagreement-Guided One-Pass Uncertainty Estimation for Medical Image Segmentation
Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);University of Applied Sciences Western Switzerland (HES-SO)(瑞士西部应用科学大学(HES-SO))
Projection-Domain Sensitivity Analysis of Vertebral DRRs Under Intrinsic Calibration Perturbation
Department of Mathematics, Tulane University(特伦特大学数学系);Department of Computer Science, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校计算机科学系);EOS, EOS Imaging Inc.(EOS公司);Department of Electrical and Computer Engineering, Vanderbilt University(范德比大学电气与计算机工程系);Department of Computer Science, Vanderbilt University(范德比大学计算机科学系)