University of Freiburg

research

∙ 08/23/2020

Robust Vision Challenge 2020 – 1st Place Report for Panoptic Segmentation

In this technical report, we present key details of our winning panoptic...

Rohit Mohan, et al. ∙

research

∙ 09/14/2021

HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO

To achieve peak predictive performance, hyperparameter optimization (HPO...

Katharina Eggensperger, et al. ∙

research

∙ 10/31/2021

Smart(Sampling)Augment: Optimal and Efficient Data Augmentation for Semantic Segmentation

Data augmentation methods enrich datasets with augmented data to improve...

Misgana Negassi, et al. ∙

research

∙ 07/19/2020

Beyond Single Stage Encoder-Decoder Networks: Deep Decoders for Semantic Image Segmentation

Single encoder-decoder methodologies for semantic segmentation are reach...

Gabriel L. Oliveira, et al. ∙

research

∙ 01/22/2020

Optimized Generic Feature Learning for Few-shot Classification across Domains

To learn models or features that generalize across tasks and domains is ...

Tonmoy Saikia, et al. ∙

research

∙ 11/25/2019

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...

Jia-Jie Zhu, et al. ∙

research

∙ 03/10/2020

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

The majority of learning-based semantic segmentation methods are optimiz...

Johan Vertens, et al. ∙

research

∙ 04/05/2020

EfficientPS: Efficient Panoptic Segmentation

Understanding the scene in which an autonomous robot operates is critica...

Rohit Mohan, et al. ∙

research

∙ 07/15/2022

USegScene: Unsupervised Learning of Depth, Optical Flow and Ego-Motion with Semantic Guidance and Coupled Networks

In this paper we propose USegScene, a framework for semantically guided ...

Johan Vertens, et al. ∙

research

∙ 12/10/2018

Defending against Universal Perturbations with Shared Adversarial Training

Classifiers such as deep neural networks have been shown to be vulnerabl...

Chaithanya Kumar Mummadi, et al. ∙

research

∙ 09/03/2019

Learning User Preferences for Trajectories from Brain Signals

Robot motions in the presence of humans should not only be feasible and ...

Henrich Kolkhorst, et al. ∙

research

∙ 05/12/2022

Localized Vision-Language Matching for Open-vocabulary Object Detection

In this work, we propose an open-world object detection method that, bas...

Maria A. Bravo, et al. ∙

research

∙ 10/11/2021

You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction

Predicting the future trajectory of a moving agent can be easy when the ...

Osama Makansi, et al. ∙

research

∙ 01/11/2022

End-To-End Optimization of LiDAR Beam Configuration for 3D Object Detection and Localization

Existing learning methods for LiDAR-based applications use 3D points sca...

Niclas Vödisch, et al. ∙

research

∙ 06/08/2020

Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior

In this paper, we investigate the problem of anticipating future dynamic...

Osama Makansi, et al. ∙

research

∙ 06/09/2019

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 ...

Osama Makansi, et al. ∙

research

∙ 08/15/2019

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

The ability to understand visual information from limited labeled data i...

Sudhanshu Mittal, et al. ∙

research

∙ 05/01/2021

Lane Graph Estimation for Scene Understanding in Urban Driving

Lane-level scene annotations provide invaluable data in autonomous vehic...

Jannik Zürn, et al. ∙

research

∙ 11/20/2020

Recovering the Imperfect: Cell Segmentation in the Presence of Dynamically Localized Proteins

Deploying off-the-shelf segmentation networks on biomedical data has bec...

Özgün Çiçek, et al. ∙

research

∙ 11/24/2021

Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning

Accurate value estimates are important for off-policy reinforcement lear...

Nicolai Dorka, et al. ∙

research

∙ 05/04/2018

Intracranial Error Detection via Deep Learning

Deep learning techniques have revolutionized the field of machine learni...

Martin Völker, et al. ∙

research

∙ 12/01/2017

The reparameterization trick for acquisition functions

Bayesian optimization is a sample-efficient approach to solving global o...

James T. Wilson, et al. ∙

research

∙ 11/14/2017

Fixing Weight Decay Regularization in Adam

We note that common implementations of adaptive gradient algorithms, suc...

Ilya Loshchilov, et al. ∙

research

∙ 11/13/2017

Simple And Efficient Architecture Search for Convolutional Neural Networks

Neural networks have recently had a lot of success for many tasks. Howev...

Thomas Elsken, et al. ∙

research

∙ 11/22/2017

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...

Sebastian Castaño-Candamil, et al. ∙

research

∙ 11/21/2017

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

Recently, there is increasing interest and research on the interpretabil...

Kay Gregor Hartmann, et al. ∙

research

∙ 08/26/2017

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

We apply convolutional neural networks (ConvNets) to the task of disting...

Robin Tibor Schirrmeister, et al. ∙

research

∙ 07/25/2017

Learning to Singulate Objects using a Push Proposal Network

A key challenge for manipulation in unstructured environments is action ...

Andreas Eitel, et al. ∙

research

∙ 10/06/2017

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...

Lei Tai, et al. ∙

research

∙ 04/19/2017

Universal Adversarial Perturbations Against Semantic Image Segmentation

While deep learning is remarkably successful on perceptual tasks, it was...

Jan-Hendrik Metzen, et al. ∙

research

∙ 09/22/2017

Predicting Runtime Distributions using Deep Neural Networks

Many state-of-the-art algorithms for solving hard combinatorial problems...

Katharina Eggensperger, et al. ∙

research

∙ 04/03/2017

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

General human action recognition requires understanding of various visua...

Mohammadreza Zolfaghari, et al. ∙

research

∙ 03/03/2017

Adversarial Examples for Semantic Image Segmentation

Machine learning methods in general and Deep Neural Networks in particul...

Volker Fischer, et al. ∙

research

∙ 07/20/2017

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...

Felix Burget, et al. ∙

research

∙ 10/04/2017

Effective Image Differencing with ConvNets for Real-time Transient Hunting

Large sky surveys are increasingly relying on image subtraction pipeline...

Nima Sedaghat, et al. ∙

research

∙ 08/13/2016

SGDR: Stochastic Gradient Descent with Warm Restarts

Restart techniques are common in gradient-free optimization to deal with...

Ilya Loshchilov, et al. ∙

research

∙ 06/29/2017

Neural SLAM: Learning to Explore with External Memory

We present an approach for agents to learn representations of a global m...

Jingwei Zhang, et al. ∙

research

∙ 05/30/2016

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...

Anh Nguyen, et al. ∙

research

∙ 04/25/2016

CMA-ES for Hyperparameter Optimization of Deep Neural Networks

Hyperparameters of deep neural networks are often optimized by grid sear...

Ilya Loshchilov, et al. ∙

research

∙ 05/17/2017

Pitfalls and Best Practices in Algorithm Configuration

Good parameter settings are crucial to achieve high performance in many ...

Katharina Eggensperger, et al. ∙

research

∙ 11/19/2015

Online Batch Selection for Faster Training of Neural Networks

Deep neural networks are commonly trained using stochastic non-convex op...

Ilya Loshchilov, et al. ∙

research

∙ 04/18/2017

Understanding Negations in Information Processing: Learning from Replicating Human Behavior

Information systems experience an ever-growing volume of unstructured da...

Nicolas Pröllochs, et al. ∙

research

∙ 07/24/2015

Multimodal Deep Learning for Robust RGB-D Object Recognition

Robust object recognition is a crucial ingredient of many, if not all, r...

Andreas Eitel, et al. ∙

research

∙ 06/09/2015

Inverting Visual Representations with Convolutional Networks

Feature representations, both hand-designed and learned ones, are often ...

Alexey Dosovitskiy, et al. ∙

research

∙ 07/27/2017

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

The original ImageNet dataset is a popular large-scale benchmark for tra...

Patryk Chrabaszcz, et al. ∙

research

∙ 12/21/2014

Striving for Simplicity: The All Convolutional Net

Most modern convolutional neural networks (CNNs) used for object recogni...

Jost Tobias Springenberg, et al. ∙

research

∙ 12/16/2016

Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments

In this paper we consider the problem of robot navigation in simple maze...

Jingwei Zhang, et al. ∙

research

∙ 12/02/2016

Asynchronous Stochastic Gradient MCMC with Elastic Coupling

We consider parallel asynchronous Markov Chain Monte Carlo (MCMC) sampli...

Jost Tobias Springenberg, et al. ∙

research

∙ 06/26/2014

Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks

Deep convolutional networks have proven to be very successful in learnin...

Alexey Dosovitskiy, et al. ∙

research

∙ 07/04/2017

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

To operate intelligently in domestic environments, robots require the ab...

Philipp Jund, et al. ∙

University of Freiburg

Featured Researchers