[PAST] Automatic Representation Learning for Visual Recognition
[PAST] Automatic Representation Learning for Visual Recognition 
2015 / 10 / 02 / PM 1:00
Location: 301 - 1420
Speaker: Bohyung Han
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 is currently an Associate Professor in the Department of Computer Science and Engineering at POSTECH, Korea. He is an Associate Editor for Computer Vision and Image Understanding and Machine Vision and Applications. He served as an Area Chair in NIPS 2015, ICCV 2015, ACCV 2012/2014 and WACV 2014, and as a Demo Chair in ACCV 2014. His current research interests include computer vision and machine learning.
I present a Bayesian evidence framework to facilitate transfer learning from pre-trained deep convolutional neural networks (CNNs). This framework is formulated on top of a least squares SVM (LS-SVM) classifier, which is simple and fast in both training and testing, and achieves competitive performance in practice. The regularization parameters in LS-SVM is estimated automatically without grid search and cross-validation by maximizing evidence, which is a useful measure to select the best performing CNN out of multiple candidates for transfer learning. I also show that the Bayesian evidence framework provides a good solution to identify the best ensemble of heterogeneous CNNs through a greedy algorithm. Our Bayesian evidence framework for transfer learning is tested on 12 visual recognition datasets and illustrates the state-of-the-art performance consistently in terms of prediction accuracy and modeling efficiency. This is a joint work with Dr. Yong-Deok Kim, Mr. Taewoong Jang and Prof. Seungjin Choi.