Technische Universität München

∙ München , Germany ∙ 0 followers

Technical University of Munich is a research university with campuses in Munich, Garching and Freising-Weihenstephan.

A Comparative Study between Bayesian and Frequentist Neural Networks for Remaining Useful Life Estimation in Condition-Based Maintenance

In the last decade, deep learning (DL) has outperformed model-based and ...
11/14/2019 ∙ by Luca Della Libera, et al. ∙ 64 ∙ share

read it
Machine Learning-Based Optimal Mesh Generation in Computational Fluid Dynamics

Computational Fluid Dynamics (CFD) is a major sub-field of engineering. ...
02/25/2021 ∙ by Keefe Huang, et al. ∙ 41 ∙ share

read it
Are we using appropriate segmentation metrics? Identifying correlates of human expert perception for CNN training beyond rolling the DICE coefficient

In this study, we explore quantitative correlates of qualitative human e...
03/10/2021 ∙ by Florian Kofler, et al. ∙ 28 ∙ share

read it
Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors

We present an automatic annotation pipeline to recover 9D cuboids and 3D...
11/26/2019 ∙ by Sergey Zakharov, et al. ∙ 23 ∙ share

read it
Adversarial Convolutional Networks with Weak Domain-Transfer for Multi-Sequence Cardiac MR Images Segmentation

Analysis and modeling of the ventricles and myocardium are important in ...
08/25/2019 ∙ by Jingkun Chen, et al. ∙ 21 ∙ share

read it
Enabling Un-/Semi-Supervised Machine Learning for MDSE of the Real-World CPS/IoT Applications

In this paper, we propose a novel approach to support domain-specific Mo...
07/06/2021 ∙ by Armin Moin, et al. ∙ 20 ∙ share

read it
WeatherBench: A benchmark dataset for data-driven weather forecasting

Data-driven approaches, most prominently deep learning, have become powe...
02/02/2020 ∙ by Stephan Rasp, et al. ∙ 19 ∙ share

read it
Predictive Collective Variable Discovery with Deep Bayesian Models

Extending spatio-temporal scale limitations of models for complex atomis...
09/18/2018 ∙ by Markus Schöberl, et al. ∙ 18 ∙ share

read it
clDice – a Topology-Preserving Loss Function for Tubular Structure Segmentation

Accurate segmentation of tubular, network-like structures, such as vesse...
03/16/2020 ∙ by Suprosanna, et al. ∙ 18 ∙ share

read it
Hierarchical Feature Embedding for Attribute Recognition

Attribute recognition is a crucial but challenging task due to viewpoint...
05/23/2020 ∙ by Jie Yang, et al. ∙ 18 ∙ share

read it
Generalized Zero and Few-Shot Transfer for Facial Forgery Detection

We propose Deep Distribution Transfer(DDT), a new transfer learning appr...
06/21/2020 ∙ by Shivangi Aneja, et al. ∙ 18 ∙ share

read it
e-UDA: Efficient Unsupervised Domain Adaptation for Cross-Site Medical Image Segmentation

Domain adaptation in healthcare data is a potentially critical component...
01/25/2020 ∙ by Hongwei Li, et al. ∙ 17 ∙ share

read it
ERA: A Dataset and Deep Learning Benchmark for Event Recognition in Aerial Videos

Along with the increasing use of unmanned aerial vehicles (UAVs), large ...
01/30/2020 ∙ by Lichao Mou, et al. ∙ 16 ∙ share

read it
A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection

Object detection in camera images, using deep learning has been proven s...
05/15/2020 ∙ by Felix Nobis, et al. ∙ 16 ∙ share

read it
Learning a Neural Solver for Multiple Object Tracking

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) w...
12/16/2019 ∙ by Guillem Brasó, et al. ∙ 15 ∙ share

read it
On Linear Interpolation in the Latent Space of Deep Generative Models

The underlying geometrical structure of the latent space in deep generat...
05/08/2021 ∙ by Mike Yan Michelis, et al. ∙ 15 ∙ share

read it
Undecidability of Learnability

Machine learning researchers and practitioners steadily enlarge the mult...
06/02/2021 ∙ by Matthias C. Caro, et al. ∙ 15 ∙ share

read it
FutureGAN: Anticipating the Future Frames of Video Sequences using Spatio-Temporal 3d Convolutions in Progressively Growing Autoencoder GANs

We propose a new Autoencoder GAN model, FutureGAN, that predicts future ...
10/02/2018 ∙ by Sandra Aigner, et al. ∙ 14 ∙ share

read it
SteReFo: Efficient Image Refocusing with Stereo Vision

Whether to attract viewer attention to a particular object, give the imp...
09/29/2019 ∙ by Benjamin Busam, et al. ∙ 14 ∙ share

read it
Inferring Super-Resolution Depth from a Moving Light-Source Enhanced RGB-D Sensor: A Variational Approach

A novel approach towards depth map super-resolution using multi-view unc...
12/13/2019 ∙ by Lu Sang, et al. ∙ 14 ∙ share

read it
Learning Graph Embeddings for Compositional Zero-shot Learning

In compositional zero-shot learning, the goal is to recognize unseen com...
02/03/2021 ∙ by Muhammad Ferjad Naeem, et al. ∙ 14 ∙ share

read it
MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification

We introduce MultiDepth, a novel training strategy and convolutional neu...
07/25/2019 ∙ by Lukas Liebel, et al. ∙ 12 ∙ share

read it
Planning from Images with Deep Latent Gaussian Process Dynamics

Planning is a powerful approach to control problems with known environme...
05/07/2020 ∙ by Nathanael Bosch, et al. ∙ 12 ∙ share

read it
CorNet: Generic 3D Corners for 6D Pose Estimation of New Objects without Retraining

We present a novel approach to the detection and 3D pose estimation of o...
08/29/2019 ∙ by Giorgia Pitteri, et al. ∙ 11 ∙ share

read it
HistoNet: Predicting size histograms of object instances

We propose to predict histograms of object sizes in crowded scenes direc...
12/11/2019 ∙ by Kishan Sharma, et al. ∙ 11 ∙ share

read it
Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning

In this paper we introduce the first reinforcement learning (RL) based r...
03/30/2020 ∙ by Hannes Hase, et al. ∙ 11 ∙ share

read it
A Road-map to Robot Task Execution with the Functional Object-Oriented Network

Following work on joint object-action representations, the functional ob...
06/01/2021 ∙ by David Paulius, et al. ∙ 11 ∙ share

read it
Parsing Geometry Using Structure-Aware Shape Templates

Real-life man-made objects often exhibit strong and easily-identifiable ...
08/03/2018 ∙ by Vignesh Ganapathi-Subramanian, et al. ∙ 10 ∙ share

read it
An Optical Flow-Based Approach for Minimally-Divergent Velocimetry Data Interpolation

Three-dimensional (3D) biomedical image sets are often acquired with in-...
12/20/2018 ∙ by Berkay Kanberoglu, et al. ∙ 10 ∙ share

read it
Tracking without bells and whistles

The problem of tracking multiple objects in a video sequence poses sever...
03/13/2019 ∙ by Philipp Bergmann, et al. ∙ 10 ∙ share

read it
Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools

Deep Learning (DL) has had an immense success in the recent past, leadin...
03/27/2019 ∙ by Ruben Mayer, et al. ∙ 10 ∙ share

read it
Generating Reliable Process Event Streams and Time Series Data based on Neural Networks

Domains such as manufacturing and medicine crave for continuous monitori...
03/09/2021 ∙ by Tobias Herbert, et al. ∙ 10 ∙ share

read it
Developmental Stage Classification of Embryos Using Two-Stream Neural Network with Linear-Chain Conditional Random Field

The developmental process of embryos follows a monotonic order. An embry...
07/13/2021 ∙ by Stanislav Lukyanenko, et al. ∙ 10 ∙ share

read it
A Review on Neural Network Models of Schizophrenia and Autism Spectrum Disorder

This survey presents the most relevant neural network models of autism s...
06/24/2019 ∙ by Pablo Lanillos, et al. ∙ 9 ∙ share

read it
Force-Ultrasound Fusion: Bringing Spine Robotic-US to the Next "Level"

Spine injections are commonly performed in several clinical procedures. ...
02/26/2020 ∙ by Maria Tirindelli, et al. ∙ 9 ∙ share

read it
Spatiotemporal-Aware Augmented Reality: Redefining HCI in Image-Guided Therapy

Suboptimal interaction with patient data and challenges in mastering 3D ...
03/04/2020 ∙ by Javad Fotouhi, et al. ∙ 9 ∙ share

read it
Indirect and Direct Training of Spiking Neural Networks for End-to-End Control of a Lane-Keeping Vehicle

Building spiking neural networks (SNNs) based on biological synaptic pla...
03/10/2020 ∙ by Zhenshan Bing, et al. ∙ 9 ∙ share

read it
Spatio-temporal Learning from Longitudinal Data for Multiple Sclerosis Lesion Segmentation

Segmentation of Multiple Sclerosis (MS) lesions in longitudinal brain MR...
04/07/2020 ∙ by Stefan Denner, et al. ∙ 9 ∙ share

read it
Recurrently Exploring Class-wise Attention in A Hybrid Convolutional and Bidirectional LSTM Network for Multi-label Aerial Image Classification

Aerial image classification is of great significance in remote sensing c...
07/30/2018 ∙ by Yuansheng Hua, et al. ∙ 8 ∙ share

read it
CVPR19 Tracking and Detection Challenge: How crowded can it get?

Standardized benchmarks are crucial for the majority of computer vision ...
06/10/2019 ∙ by Patrick Dendorfer, et al. ∙ 8 ∙ share

read it
Object-Driven Multi-Layer Scene Decomposition From a Single Image

We present a method that tackles the challenge of predicting color and d...
08/26/2019 ∙ by Helisa Dhamo, et al. ∙ 8 ∙ share

read it
Self6D: Self-Supervised Monocular 6D Object Pose Estimation

Estimating the 6D object pose is a fundamental problem in computer visio...
04/14/2020 ∙ by Gu Wang, et al. ∙ 8 ∙ share

read it
Red-GAN: Attacking class imbalance via conditioned generation. Yet another medical imaging perspective

Exploiting learning algorithms under scarce data regimes is a limitation...
04/22/2020 ∙ by Ahmad B Qasim, et al. ∙ 8 ∙ share

read it
Decision Support for Intoxication Prediction Using Graph Convolutional Networks

Every day, poison control centers (PCC) are called for immediate classif...
05/02/2020 ∙ by Hendrik Burwinkel, et al. ∙ 8 ∙ share

read it
Cross-Task Transfer for Multimodal Aerial Scene Recognition

Aerial scene recognition is a fundamental task in remote sensing and has...
05/18/2020 ∙ by Di Hu, et al. ∙ 8 ∙ share

read it
Temporally Coherent GANs for Video Super-Resolution (TecoGAN)

Adversarial training has been highly successful in the context of image ...
11/23/2018 ∙ by Mengyu Chu, et al. ∙ 7 ∙ share

read it
From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds

We propose a new method for segmentation-free joint estimation of orthog...
01/21/2020 ∙ by Christiane Sommer, et al. ∙ 7 ∙ share

read it
METGAN: Generative Tumour Inpainting and Modality Synthesis in Light Sheet Microscopy

Novel multimodal imaging methods are capable of generating extensive, su...
04/22/2021 ∙ by Izabela Horvath, et al. ∙ 7 ∙ share

read it
Multi-Source Neural Variational Inference

Learning from multiple sources of information is an important problem in...
11/11/2018 ∙ by Richard Kurle, et al. ∙ 6 ∙ share

read it
Deferred Neural Rendering: Image Synthesis using Neural Textures

The modern computer graphics pipeline can synthesize images at remarkabl...
04/28/2019 ∙ by Justus Thies, et al. ∙ 6 ∙ share

read it

Technische Universität München

Featured Researchers