logo Idiap Research Institute        
 [BibTeX] [Marc21]
Improving Object Classification using Pose Information
Type of publication: Idiap-RR
Citation: Penedones_Idiap-RR-30-2012
Number: Idiap-RR-30-2012
Year: 2012
Month: 11
Institution: Idiap
Abstract: 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.
Projects Idiap
Authors Penedones, Hugo
Collobert, Ronan
Fleuret, Francois
Grangier, David
Added by: [ADM]
Total mark: 0
  • Penedones_Idiap-RR-30-2012.pdf (MD5: b1efb218791e9a1e1a771a3b3c2c53c0)