University of Freiburg

∙ Freiburg , Germany ∙ 0 followers

Infos&Research News of the Press Office of the University of Freiburg. https://t.co/8AFw26eMgf https://t.co/7krbiIzbrt

Optimized Generic Feature Learning for Few-shot Classification across Domains

To learn models or features that generalize across tasks and domains is ...
01/22/2020 ∙ by Tonmoy Saikia, et al. ∙ 18 ∙ share

read it
A New Distribution-Free Concept for Representing, Comparing, and Propagating Uncertainty in Dynamical Systems with Kernel Probabilistic Programming

This work presents the concept of kernel mean embedding and kernel proba...
11/25/2019 ∙ by Jia-Jie Zhu, et al. ∙ 17 ∙ share

read it
HeatNet: Bridging the Day-Night Domain Gap in Semantic Segmentation with Thermal Images

The majority of learning-based semantic segmentation methods are optimiz...
03/10/2020 ∙ by Johan Vertens, et al. ∙ 16 ∙ share

read it
EfficientPS: Efficient Panoptic Segmentation

Understanding the scene in which an autonomous robot operates is critica...
04/05/2020 ∙ by Rohit Mohan, et al. ∙ 16 ∙ share

read it
Defending against Universal Perturbations with Shared Adversarial Training

Classifiers such as deep neural networks have been shown to be vulnerabl...
12/10/2018 ∙ by Chaithanya Kumar Mummadi, et al. ∙ 12 ∙ share

read it
Learning User Preferences for Trajectories from Brain Signals

Robot motions in the presence of humans should not only be feasible and ...
09/03/2019 ∙ by Henrich Kolkhorst, et al. ∙ 12 ∙ share

read it
Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction

Future prediction is a fundamental principle of intelligence that helps ...
06/09/2019 ∙ by Osama Makansi, et al. ∙ 8 ∙ share

read it
Semi-Supervised Semantic Segmentation with High- and Low-level Consistency

The ability to understand visual information from limited labeled data i...
08/15/2019 ∙ by Sudhanshu Mittal, et al. ∙ 5 ∙ share

read it
Intracranial Error Detection via Deep Learning

Deep learning techniques have revolutionized the field of machine learni...
05/04/2018 ∙ by Martin Völker, et al. ∙ 2 ∙ share

read it
The reparameterization trick for acquisition functions

Bayesian optimization is a sample-efficient approach to solving global o...
12/01/2017 ∙ by James T. Wilson, et al. ∙ 0 ∙ share

read it
Fixing Weight Decay Regularization in Adam

We note that common implementations of adaptive gradient algorithms, suc...
11/14/2017 ∙ by Ilya Loshchilov, et al. ∙ 0 ∙ share

read it
Simple And Efficient Architecture Search for Convolutional Neural Networks

Neural networks have recently had a lot of success for many tasks. Howev...
11/13/2017 ∙ by Thomas Elsken, et al. ∙ 0 ∙ share

read it
Post-hoc labeling of arbitrary EEG recordings for data-efficient evaluation of neural decoding methods

Many cognitive, sensory and motor processes have correlates in oscillato...
11/22/2017 ∙ by Sebastian Castaño-Candamil, et al. ∙ 0 ∙ share

read it
Hierarchical internal representation of spectral features in deep convolutional networks trained for EEG decoding

Recently, there is increasing interest and research on the interpretabil...
11/21/2017 ∙ by Kay Gregor Hartmann, et al. ∙ 0 ∙ share

read it
Deep learning with convolutional neural networks for decoding and visualization of EEG pathology

We apply convolutional neural networks (ConvNets) to the task of disting...
08/26/2017 ∙ by Robin Tibor Schirrmeister, et al. ∙ 0 ∙ share

read it
Learning to Singulate Objects using a Push Proposal Network

A key challenge for manipulation in unstructured environments is action ...
07/25/2017 ∙ by Andreas Eitel, et al. ∙ 0 ∙ share

read it
Socially-compliant Navigation through Raw Depth Inputs with Generative Adversarial Imitation Learning

We present an approach for mobile robots to learn to navigate in pedestr...
10/06/2017 ∙ by Lei Tai, et al. ∙ 0 ∙ share

read it
Universal Adversarial Perturbations Against Semantic Image Segmentation

While deep learning is remarkably successful on perceptual tasks, it was...
04/19/2017 ∙ by Jan-Hendrik Metzen, et al. ∙ 0 ∙ share

read it
Predicting Runtime Distributions using Deep Neural Networks

Many state-of-the-art algorithms for solving hard combinatorial problems...
09/22/2017 ∙ by Katharina Eggensperger, et al. ∙ 0 ∙ share

read it
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection

General human action recognition requires understanding of various visua...
04/03/2017 ∙ by Mohammadreza Zolfaghari, et al. ∙ 0 ∙ share

read it
Adversarial Examples for Semantic Image Segmentation

Machine learning methods in general and Deep Neural Networks in particul...
03/03/2017 ∙ by Volker Fischer, et al. ∙ 0 ∙ share

read it
Acting Thoughts: Towards a Mobile Robotic Service Assistant for Users with Limited Communication Skills

As autonomous service robots become more affordable and thus available a...
07/20/2017 ∙ by Felix Burget, et al. ∙ 0 ∙ share

read it
Effective Image Differencing with ConvNets for Real-time Transient Hunting

Large sky surveys are increasingly relying on image subtraction pipeline...
10/04/2017 ∙ by Nima Sedaghat, et al. ∙ 0 ∙ share

read it
SGDR: Stochastic Gradient Descent with Warm Restarts

Restart techniques are common in gradient-free optimization to deal with...
08/13/2016 ∙ by Ilya Loshchilov, et al. ∙ 0 ∙ share

read it
Neural SLAM: Learning to Explore with External Memory

We present an approach for agents to learn representations of a global m...
06/29/2017 ∙ by Jingwei Zhang, et al. ∙ 0 ∙ share

read it
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks

Deep neural networks (DNNs) have demonstrated state-of-the-art results o...
05/30/2016 ∙ by Anh Nguyen, et al. ∙ 0 ∙ share

read it
CMA-ES for Hyperparameter Optimization of Deep Neural Networks

Hyperparameters of deep neural networks are often optimized by grid sear...
04/25/2016 ∙ by Ilya Loshchilov, et al. ∙ 0 ∙ share

read it
Pitfalls and Best Practices in Algorithm Configuration

Good parameter settings are crucial to achieve high performance in many ...
05/17/2017 ∙ by Katharina Eggensperger, et al. ∙ 0 ∙ share

read it
Online Batch Selection for Faster Training of Neural Networks

Deep neural networks are commonly trained using stochastic non-convex op...
11/19/2015 ∙ by Ilya Loshchilov, et al. ∙ 0 ∙ share

read it
Understanding Negations in Information Processing: Learning from Replicating Human Behavior

Information systems experience an ever-growing volume of unstructured da...
04/18/2017 ∙ by Nicolas Pröllochs, et al. ∙ 0 ∙ share

read it
Multimodal Deep Learning for Robust RGB-D Object Recognition

Robust object recognition is a crucial ingredient of many, if not all, r...
07/24/2015 ∙ by Andreas Eitel, et al. ∙ 0 ∙ share

read it
Inverting Visual Representations with Convolutional Networks

Feature representations, both hand-designed and learned ones, are often ...
06/09/2015 ∙ by Alexey Dosovitskiy, et al. ∙ 0 ∙ share

read it
A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets

The original ImageNet dataset is a popular large-scale benchmark for tra...
07/27/2017 ∙ by Patryk Chrabaszcz, et al. ∙ 0 ∙ share

read it
Striving for Simplicity: The All Convolutional Net

Most modern convolutional neural networks (CNNs) used for object recogni...
12/21/2014 ∙ by Jost Tobias Springenberg, et al. ∙ 0 ∙ share

read it
Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments

In this paper we consider the problem of robot navigation in simple maze...
12/16/2016 ∙ by Jingwei Zhang, et al. ∙ 0 ∙ share

read it
Asynchronous Stochastic Gradient MCMC with Elastic Coupling

We consider parallel asynchronous Markov Chain Monte Carlo (MCMC) sampli...
12/02/2016 ∙ by Jost Tobias Springenberg, et al. ∙ 0 ∙ share

read it
Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks

Deep convolutional networks have proven to be very successful in learnin...
06/26/2014 ∙ by Alexey Dosovitskiy, et al. ∙ 0 ∙ share

read it
Optimization Beyond the Convolution: Generalizing Spatial Relations with End-to-End Metric Learning

To operate intelligently in domestic environments, robots require the ab...
07/04/2017 ∙ by Philipp Jund, et al. ∙ 0 ∙ share

read it
Topometric Localization with Deep Learning

Compared to LiDAR-based localization methods, which provide high accurac...
06/27/2017 ∙ by Gabriel L. Oliveira, et al. ∙ 0 ∙ share

read it
Unsupervised feature learning by augmenting single images

When deep learning is applied to visual object recognition, data augment...
12/18/2013 ∙ by Alexey Dosovitskiy, et al. ∙ 0 ∙ share

read it
Instrumenting an SMT Solver to Solve Hybrid Network Reachability Problems

PDDL+ planning has its semantics rooted in hybrid automata (HA) and rece...
09/13/2016 ∙ by Daniel Bryce, et al. ∙ 0 ∙ share

read it
Learning from Label Proportions in Brain-Computer Interfaces: Online Unsupervised Learning with Guarantees

Objective: Using traditional approaches, a Brain-Computer Interface (BCI...
01/25/2017 ∙ by D Hübner, et al. ∙ 0 ∙ share

read it
Learning to Estimate 3D Hand Pose from Single RGB Images

Low-cost consumer depth cameras and deep learning have enabled reasonabl...
05/03/2017 ∙ by Christian Zimmermann, et al. ∙ 0 ∙ share

read it
The Configurable SAT Solver Challenge (CSSC)

It is well known that different solution strategies work well for differ...
05/05/2015 ∙ by Frank Hutter, et al. ∙ 0 ∙ share

read it
Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets

Bayesian optimization has become a successful tool for hyperparameter op...
05/23/2016 ∙ by Aaron Klein, et al. ∙ 0 ∙ share

read it
Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild

CNN-based optical flow estimation has attracted attention recently, main...
12/12/2016 ∙ by Nima Sedaghat, et al. ∙ 0 ∙ share

read it
Computing AIC for black-box models using Generalised Degrees of Freedom: a comparison with cross-validation

Generalised Degrees of Freedom (GDF), as defined by Ye (1998 JASA 93:120...
03/09/2016 ∙ by Severin Hauenstein, et al. ∙ 0 ∙ share

read it
A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

Recent work has shown that optical flow estimation can be formulated as ...
12/07/2015 ∙ by Nikolaus Mayer, et al. ∙ 0 ∙ share

read it
Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks

In this paper we present a method for learning a discriminative classifi...
11/19/2015 ∙ by Jost Tobias Springenberg, et al. ∙ 0 ∙ share

read it
Object Detection, Tracking, and Motion Segmentation for Object-level Video Segmentation

We present an approach for object segmentation in videos that combines f...
08/10/2016 ∙ by Benjamin Drayer, et al. ∙ 0 ∙ share

read it

University of Freiburg

Featured Researchers