HONG KONG BAPTIST UNIVERSITY
FACULTY OF SCIENCE
Department of Computer Science Colloquium
Efficient Supervision Schemes for Object Detection, Segmentation, and 3D Reconstruction
Prof. Vittorio Ferrari
Research Group on Visual Learning
Date: April 17, 2019 (Wednesday)
Time: 4:30 - 5:30 pm
Venue: SCT909, Cha Chi Ming Science Tower, Ho Sin Hang Campus
A key goal of computer vision is to interpret images of complex scenes, which involves several tasks such as recognizing objects, localizing them in the image, and estimating their shape in the 3D world. To achieve this we need rich models capturing the diversity of the visual world. However, training such models typically requires tedious and time consuming manual annotation, which hinders scaling to a large number of objects and many training samples. In this talk I will present recent techniques from my team for reducing the amount of supervision required to train models for various scene understanding tasks, including object detection, semantic segmentation, and single-view 3D reconstruction. I will focus especially on human-machine collaboration scenarios, where the machine assists a human in annotating the training data and training a new model. These techniques hit a particularly sweet spot in the trade-off between the quality of the learned models and human supervision time.
Vittorio Ferrari leads a research group on visual learning at Google. He received his PhD from ETH Zurich in 2004, then was a post-doc at INRIA Grenoble (2006-2007) and at the University of Oxford (2007-2008). Between 2008 and 2012 he was an Assistant Professor at ETH Zurich, funded by a Swiss National Science Foundation Professorship grant. In 2012-2018 he was faculty at the University of Edinburgh, where he became a Full Professor in 2016. In 2012 he received the prestigious ERC Starting Grant, and the best paper award from the European Conference in Computer Vision. He is the author of over 110 technical publications. He regularly serves as an Area Chair for the major computer vision conferences, he was a Program Chair for ECCV 2018 and will be a General Chair for ECCV 2020. He is an Associate Editor of IEEE Pattern Analysis and Machine Intelligence. His current research interests are in learning visual models with minimal human supervision, human-machine collaboration, and semantic segmentation.
********* ALL INTERESTED ARE WELCOME ***********
(For enquiry, please contact Computer Science Department at 3411 2385)
Department of Computer Science, Hong Kong Baptist University