70 citations · 102 across the 10 of their papers we have counts for
7 papers · 1 filter
Performing Arithmetic Using a Neural Network Trained on Digit Permutation Pairs
Marcus D. Bloice, Peter M. Roth, Andreas Holzinger
In this paper a neural network is trained to perform simple arithmetic using images of concatenated handwritten digit pairs. A convolutional neural network was trained with images…
Patch augmentation: Towards efficient decision boundaries for neural networks
Marcus D. Bloice, Peter M. Roth, Andreas Holzinger
In this paper we propose a new augmentation technique, called patch augmentation, that, in our experiments, improves model accuracy and makes networks more robust to adversarial at…
L*ReLU: Piece-wise Linear Activation Functions for Deep Fine-grained Visual Categorization
Mina Basirat, Peter M. Roth
Deep neural networks paved the way for significant improvements in image visual categorization during the last years. However, even though the tasks are highly varying, differing i…
Smart Hypothesis Generation for Efficient and Robust Room Layout Estimation
Martin Hirzer, Peter M. Roth, Vincent Lepetit
We propose a novel method to efficiently estimate the spatial layout of a room from a single monocular RGB image. As existing approaches based on low-level feature extraction, foll…
Location Field Descriptors: Single Image 3D Model Retrieval in the Wild
Alexander Grabner, Peter M. Roth, Vincent Lepetit
We present Location Field Descriptors, a novel approach for single image 3D model retrieval in the wild. In contrast to previous methods that directly map 3D models and RGB images…
GP2C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the Wild
Alexander Grabner, Peter M. Roth, Vincent Lepetit
We present a joint 3D pose and focal length estimation approach for object categories in the wild. In contrast to previous methods that predict 3D poses independently of the focal…