604 citations · 1.3k across the 46 of their papers we have counts for
11 papers · 1 filter
Defending Against Universal Perturbations With Shared Adversarial Training
Chaithanya Kumar Mummadi, Thomas Brox, Jan Hendrik Metzen
Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial trainin…
Anomaly Detection With Multiple-Hypotheses Predictions
Duc Tam Nguyen, Zhongyu Lou, Michael Klar +1
In one-class-learning tasks, only the normal case (foreground) can be modeled with data, whereas the variation of all possible anomalies is too erratic to be described by samples.…
FusionNet and AugmentedFlowNet: Selective Proxy Ground Truth for Training on Unlabeled Images
Osama Makansi, Eddy Ilg, Thomas Brox
Recent work has shown that convolutional neural networks (CNNs) can be used to estimate optical flow with high quality and fast runtime. This makes them preferable for real-world a…
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation
Eddy Ilg, Tonmoy Saikia, Margret Keuper +1
Occlusions play an important role in disparity and optical flow estimation, since matching costs are not available in occluded areas and occlusions indicate depth or motion boundar…
DeepTAM: Deep Tracking and Mapping
Huizhong Zhou, Benjamin Ummenhofer, Thomas Brox
We present a system for keyframe-based dense camera tracking and depth map estimation that is entirely learned. For tracking, we estimate small pose increments between the current…
TD or not TD: Analyzing the Role of Temporal Differencing in Deep Reinforcement Learning
Artemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun +1
Our understanding of reinforcement learning (RL) has been shaped by theoretical and empirical results that were obtained decades ago using tabular representations and linear functi…