Departement Informatik, Universität Basel
Departement Informatik, Universität Basel
Departement Informatik, Universität Basel
Departement Informatik, Universität Basel

Colloquium - 17.10.2017

TitleDeep Learning for Deformable Objects
SpeakerStefanos Zafeiriou, Reader (Associate Professor++), Imperial College London
TimeTuesday, October 17, 2017 from 12:15 – 13:15
LocationDepartment of Mathematics and Computer Science, Seminar Room 05.002, University of Basel, Spiegelgasse 5, Basel

Abstract

Deep convolutional neural networks (DCNNs) are currently the predominant paradigm for learning from labeled data in computer vision applications. For example DCNN architectures are the methods of choice for object recognition, detection, as well as semantic segmentation. In this talk, I will demonstrate how DCNNs can be used to model deformable objects. That is, I will start by briefly introducing the problem of statistical deformable model fitting using non-linear least squares and I will show how machine learning has reformulated the problem. Then I will demonstrate a general DCNN plus Recurrent Neural Network (RNN) architecture for solving non-linear least squares. I will take a step further and demonstrate how fully convolutional neural networks can be used for fitting deformable 3D models, as well as for estimating properties of 3D objects, e.g. surface normals.


After the talk an informal apéro will be offered. I hope you’ll be joining us.