國立清華大學資訊工程學系

Department of Computer Science

National Tsing Hua University

專題演講

SEMINAR

主講人：邱維辰教授

SPEAKER (交大資工系)

題　目：Showcase of Making Deep Networks Explainable

TOPIC 

時  間：109年12月16日(三)下午13點30分至15點

DATE　　

地　點：台達館106,107教室

PLACE

Abstract

Recent advances in deep learning have brought the magic leap to various research areas, such as computer vision and natural image processing. However, these deep models are typically treated as powerful black boxes to transfer from the input data to the output prediction while being non-explainable or uninterpretable for our human users. Therefore, finding ways to decipher the physical meanings behind these deep models become a crucial but challenging problem. In this talk, I will try to showcase two recent works from my research group for making deep models more explainable or interpretable, with special focuses on two applications: image-to-image translation for medical images, and monocular depth estimation. We hope such attempts would bring audience inspirations or different perspectives for developing deep learning techniques.

Bio: Wei-Chen Chiu (邱維辰) received the B.S. degree in Electrical Engineering and Computer Science and the M.S. degree in Computer Science from National Chiao Tung University (Hsinchu, Taiwan) in 2008 and 2009 respectively. He further received Doctor of Engineering Science (Dr.-Ing.) from Max Planck Institute for Informatics (Saarbrücken, Germany) in 2016. He joined Department of Computer Science, National Chiao Tung University as an assistant professor from August 2017 and established the Enriched Vision Applications Laboratory. He was a postdoctoral researcher in Research Center for Information Technology Innovation, Academia Sinica, from Feb. to July. 2017, and a research scientist in a Taiwanese startup, Viscovery, from Aug. 2016 to Jan. 2017. His current research interests generally include computer vision, machine learning, and deep learning, with special focus on generative models.

    聯絡人：周志遠 教授