Improving Object Classification using Pose Information
Hugo Penedones, Ronan Collobert, François Fleuret, David Grangier · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · 2012
We propose a method that exploits pose information in order to improve object classification. A lot of research has focused in other strategies, such as engineering feature extractors, trying different classifiers and even using transfer learning. Here, we use neural network architectures in a multi-task setup, whose outputs predict both the class and the camera azimuth. We investigate both Multi-layer Perceptrons and Convolutional Neural Network architectures, and achieve state-of-the-art results in the challenging NORB dataset.