2.6k citations · 9.3k across the 89 of their papers we have counts for
18 papers · 1 filter
Parting with Illusions about Deep Active Learning
Sudhanshu Mittal, Maxim Tatarchenko, Özgün Çiçek +1
Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Rece…
Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics
Oier Mees, Maxim Tatarchenko, Thomas Brox +1
We present a convolutional neural network for joint 3D shape prediction and viewpoint estimation from a single input image. During training, our network gets the learning signal fr…
SELF: Learning to Filter Noisy Labels with Self-Ensembling
Duc Tam Nguyen, Chaithanya Kumar Mummadi, Thi Phuong Nhung Ngo +3
Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time. To overcome this problem, we present a simple and eff…
Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control
Lukas Hermann, Max Argus, Andreas Eitel +3
We propose Adaptive Curriculum Generation from Demonstrations (ACGD) for reinforcement learning in the presence of sparse rewards. Rather than designing shaped reward functions, AC…
FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images
Christian Zimmermann, Duygu Ceylan, Jimei Yang +3
Estimating 3D hand pose from single RGB images is a highly ambiguous problem that relies on an unbiased training dataset. In this paper, we analyze cross-dataset generalization whe…
DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervision
Duc Tam Nguyen, Maximilian Dax, Chaithanya Kumar Mummadi +4
Deep neural network (DNN) based salient object detection in images based on high-quality labels is expensive. Alternative unsupervised approaches rely on careful selection of multi…
Understanding and Robustifying Differentiable Architecture Search
Arber Zela, Thomas Elsken, Tonmoy Saikia +3
Differentiable Architecture Search (DARTS) has attracted a lot of attention due to its simplicity and small search costs achieved by a continuous relaxation and an approximation of…
Semi-Supervised Semantic Segmentation with High- and Low-level Consistency
Sudhanshu Mittal, Maxim Tatarchenko, Thomas Brox
The ability to understand visual information from limited labeled data is an important aspect of machine learning. While image-level classification has been extensively studied in…
Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
Chaithanya Kumar Mummadi, Tim Genewein, Dan Zhang +2
Deep neural networks achieve state-of-the-art results on several tasks while increasing in complexity. It has been shown that neural networks can be pruned during training by impos…
Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
Osama Makansi, Eddy Ilg, Özgün Cicek +1
Future prediction is a fundamental principle of intelligence that helps plan actions and avoid possible dangers. As the future is uncertain to a large extent, modeling the uncertai…
Robust Learning Under Label Noise With Iterative Noise-Filtering
Duc Tam Nguyen, Thi-Phuong-Nhung Ngo, Zhongyu Lou +3
We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on t…
What Do Single-view 3D Reconstruction Networks Learn?
Maxim Tatarchenko, Stephan R. Richter, René Ranftl +3
Convolutional networks for single-view object reconstruction have shown impressive performance and have become a popular subject of research. All existing techniques are united by…
Learning Representations for Predicting Future Activities
Mohammadreza Zolfaghari, Özgün Çiçek, Syed Mohsin Ali +3
Foreseeing the future is one of the key factors of intelligence. It involves understanding of the past and current environment as well as decent experience of its possible dynamics…
AutoDispNet: Improving Disparity Estimation With AutoML
Tonmoy Saikia, Yassine Marrakchi, Arber Zela +2
Much research work in computer vision is being spent on optimizing existing network architectures to obtain a few more percentage points on benchmarks. Recent AutoML approaches pro…
MAIN: Multi-Attention Instance Network for Video Segmentation
Juan Leon Alcazar, Maria A. Bravo, Ali K. Thabet +4
Instance-level video segmentation requires a solid integration of spatial and temporal information. However, current methods rely mostly on domain-specific information (online lear…
CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth
Jose M. Facil, Benjamin Ummenhofer, Huizhong Zhou +3
Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model. Thus, chan…
CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
Aditya Bhatt, Daniel Palenicek, Boris Belousov +4
Sample efficiency is a crucial problem in deep reinforcement learning. Recent algorithms, such as REDQ and DroQ, found a way to improve the sample efficiency by increasing the upda…
Motion Perception in Reinforcement Learning with Dynamic Objects
Artemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun +1
In dynamic environments, learned controllers are supposed to take motion into account when selecting the action to be taken. However, in existing reinforcement learning works motio…