CDISE is pleased to invite you to a seminar titled “Seed, Expand, Constrain: Three Principles for Weakly-Supervised Image Segmentation”.
The lecturer: Prof. Christoph H. Lampert, Institute of Science and Technology, Austria
Semantic segmentation is a powerful step for visual scene understanding, however it is held back by the fact that it is very time-consuming and costly to collect the necessary training data. A promising way to overcome this problem is weakly-supervised training. In my talk I will introduce a new loss function for the weakly supervised training of semantic image segmentation models based on three guiding principles: to seed with weak location cues, to expand objects based on the information about which classes can occur, and to constrain the segmentations to coincide with image boundaries. I will show that training a deep convolutional network with this new loss function leads to substantially better segmentation results than previous state-of-the-art methods, and I will give insight what are the crucial components for this effect.
Christoph Lampert received the PhD degree in mathematics from the University of Bonn in 2003. In 2010 he joined the Institute of Science and Technology Austria (IST Austria) first as an Assistant Professor and since 2015 as a Professor. His research on computer vision and machine learning has won several international and national awards, including best paper prizes at CVPR and ECCV in 2008. In 2012 he was awarded an ERC Starting Grant by the European Research Council. He is an Editor of the International Journal of Computer Vision (IJCV), Action Editor of the Journal for Machine Learning Research (JMLR), and Associate Editor in Chief of the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
Non-Skoltech attendees should contact for access to the building. Seminar schedule and information can be found at http://crei.skoltech.ru/cdise/seminar/.