The success of deep learning in computer vision is partly attributed to the construction of large-scale annotated datasets such as ImageNet. However, computer vision problems often require substantial amount of human efforts to obtain accurate annotations due to dynamic aspects of class labels, needs for pixel-level labeling, and annotation ambiguities. Hence, collecting high quality large-scale annotated datasets is very time consuming and even unrealistic. This talk discusses a semantic segmentation problem, which can derive benefit from weakly supervised learning. Specifically, I present three weakly supervised semantic segmentation algorithms investigated in POSTECH Computer Vision Laboratory–a semi-supervised few-shot learning method, a transfer learning approach, and a technique based on superpixel pooling network. All algorithms have unique architectures of convolutional neural networks, and achieve the state-of-the-art performance in PASCAL VOC dataset.
Bohyung Han received the B.S. and M.S. degrees from the Department of Computer Engineering at Seoul National University, Korea, in 1997 and 2000, respectively, and the Ph.D. degree from the Department of Computer Science at the University of Maryland, College Park, MD, USA, in 2005. He was with Samsung Electronics Research and Development Center, Irvine, CA, USA, and Mobileye Vision Technologies, Princeton, NJ, USA. He is currently an Associate Professor with the Department of Computer Science and Engineering at POSTECH, Korea. He served or will be serving as an Area Chair in NIPS 2015, ICCV 2015, ACCV 2012/2014/2016, ACML 2016 and WACV 2014, a Tutorial Chair in ICCV 2019, and a Demo Chair in ACCV 2014. He is also serving as Area Editor in Computer Vision and Image Understanding and Associate Editor in Machine Vision Applications. His current research interests include computer vision and machine learning.