Search Results for author:
Found 71 papers, 13 papers with code
Criteria for Uncertainty-based Corner Cases Detection in Instance Segmentation
We also present our first results of an iterative training cycle that outperforms the baseline and where the data added to the training dataset is selected based on the corner case decision function.
AudioProtoPNet: An interpretable deep learning model for bird sound classification
Recently, scientists have proposed several deep learning models to monitor the diversity of bird species.
Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification
BAIT, a recently proposed AL strategy based on the Fisher Information, has demonstrated impressive performance across various datasets.
BirdSet: A Multi-Task Benchmark for Classification in Computational Avian Bioacoustics
Data fragmentation and opacity across studies complicate a comprehensive evaluation of model performance.
Spatio-Temporal Attention Graph Neural Network for Remaining Useful Life Prediction
Our model combines graph neural networks and temporal convolutional neural networks for spatial and temporal feature extraction, respectively.
Enhancing Multi-Objective Optimization through Machine Learning-Supported Multiphysics Simulation
This paper presents a methodological framework for training, self-optimising, and self-organising surrogate models to approximate and speed up multiobjective optimisation of technical systems based on multiphysics simulations.
Active Label Refinement for Semantic Segmentation of Satellite Images
Since these initial labels are partially erroneous, we use active learning strategies to cost-efficiently refine the labels in the second step.
Active Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers
We propose a shift towards end-to-end learning in bird sound monitoring by combining self-supervised (SSL) and deep active learning (DAL).
Unraveling the Complexity of Splitting Sequential Data: Tackling Challenges in Video and Time Series Analysis
Splitting of sequential data, such as videos and time series, is an essential step in various data analysis tasks, including object tracking and anomaly detection.
The IMPTC Dataset: An Infrastructural Multi-Person Trajectory and Context Dataset
In addition, to enable the entire stack of research capabilities, the dataset includes all data, starting from the sensor-, calibration- and detection data until trajectory and context data.
Smart Infrastructure: A Research Junction
In addition, the junction features a highly accurate digital twin.
DADO -- Low-Cost Query Strategies for Deep Active Design Optimization
We present two selection strategies for self-optimization to reduce the computational cost in multi-objective design optimization problems.
ActiveGLAE: A Benchmark for Deep Active Learning with Transformers
Deep active learning (DAL) seeks to reduce annotation costs by enabling the model to actively query instance annotations from which it expects to learn the most.
Sampling-based Uncertainty Estimation for an Instance Segmentation Network
The examination of uncertainty in the predictions of machine learning (ML) models is receiving increasing attention.
Dataset of a parameterized U-bend flow for Deep Learning Applications
This third representation enables considering the specific data structure of numerical simulations for deep learning approaches.
Sensor Equivariance by LiDAR Projection Images
This addresses the issue of sensor-dependent object representation in projection-based sensors, such as LiDAR, which can lead to distorted physical and geometric properties due to variations in sensor resolution and field of view.
Multi-annotator Deep Learning: A Probabilistic Framework for Classification
Training standard deep neural networks leads to subpar performances in such multi-annotator supervised learning settings.
Space, Time, and Interaction: A Taxonomy of Corner Cases in Trajectory Datasets for Automated Driving
Based on these predictions - and additional contextual information such as the course of the road, (traffic) rules, and interaction with other road users - the highly automated vehicle (HAV) must be able to reliably and safely perform the task assigned to it, e. g., moving from point A to B.
Fast Bayesian Updates for Deep Learning with a Use Case in Active Learning
Retraining deep neural networks when new data arrives is typically computationally expensive.
A Review of Uncertainty Calibration in Pretrained Object Detectors
In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e. g., two-stage or set-based) and architectures (e. g., Faster-RCNN or DETR) which enable outstanding performance on challenging benchmark datasets.
Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time-Series Forecast
The proposed architecture significantly improves up to 25 percent for multi-task learning for power forecasts on the EuropeWindFarm and GermanSolarFarm dataset compared to the multi-layer perceptron approach.
Model Selection, Adaptation, and Combination for Transfer Learning in Wind and Photovoltaic Power Forecasts
Therefore, we adopt source models based on target data from different seasons and limit the amount of training data.
Synthetic Photovoltaic and Wind Power Forecasting Data
Since the synthetic time series are based exclusively on weather measurements, possible errors in the weather forecast are comparable to those in actual power data.
Design of Explainability Module with Experts in the Loop for Visualization and Dynamic Adjustment of Continual Learning
With the help of this module, experts can be more confident in decision-making regarding anomaly filtering, dynamic adjustment of hyperparameters, data backup, etc.
Towards Organic Distribution Systems -- The Vision of Self-Configuring, Self-Organising, Self-Healing, and Self-Optimising Power Distribution Management
On the grid level, distribution management systems (DMS) try to keep the power system in the normal operational state.
A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification
Therefore, we introduce a general real-world AL strategy as part of a learning cycle and use its elements, e. g., the query and annotator selection algorithm, to categorize about 60 real-world AL strategies.
Description of Corner Cases in Automated Driving: Goals and Challenges
Scaling the distribution of automated vehicles requires handling various unexpected and possibly dangerous situations, termed corner cases (CC).
Artificial intelligence for online characterization of ultrashort X-ray free-electron laser pulses
X-ray free-electron lasers (XFELs) as the world's brightest light sources provide ultrashort X-ray pulses with a duration typically in the order of femtoseconds.
Probabilistic Active Learning for Active Class Selection
In machine learning, active class selection (ACS) algorithms aim to actively select a class and ask the oracle to provide an instance for that class to optimize a classifier's performance while minimizing the number of requests.
Cyclist Trajectory Forecasts by Incorporation of Multi-View Video Information
This article presents a novel approach to incorporate visual cues from video-data from a wide-angle stereo camera system mounted at an urban intersection into the forecast of cyclist trajectories.
Pose and Semantic Map Based Probabilistic Forecast of Vulnerable Road Users' Trajectories
We compare our method with an approach that provides forecasts in the form of Gaussian distributions and discuss the respective advantages and disadvantages.
Out-of-distribution Detection and Generation using Soft Brownian Offset Sampling and Autoencoders
For this purpose, we propose a novel approach that allows for the generation of out-of-distribution datasets based on a given in-distribution dataset.
Cyclist Intention Detection: A Probabilistic Approach
A basic movement detection based on motion history images (MHI) and a residual convolutional neural network (ResNet) are used to estimate probabilities for the current cyclist motion state.
An Application-Driven Conceptualization of Corner Cases for Perception in Highly Automated Driving
Systems and functions that rely on machine learning (ML) are the basis of highly automated driving.
AdaPT: Adaptable Particle Tracking for Spherical Microparticles in Lab on Chip Systems
In the following, we distinguish between two sub-steps in particle tracking, namely the localization of particles in single images and the linking of the extracted particle positions of the subsequent frames into trajectories.
Data Analysis, Statistics and Probability
CLeaR: An Adaptive Continual Learning Framework for Regression Tasks
The second one is designed with data collected from European wind farms to evaluate the CLeaR framework's performance in a real-world application.
Quantile Surfaces -- Generalizing Quantile Regression to Multivariate Targets
In this article, we present a novel approach to multivariate probabilistic forecasting.
Efficient SVDD Sampling with Approximation Guarantees for the Decision Boundary
Our approach is to frame SVDD sampling as an optimization problem, where constraints guarantee that sampling indeed approximates the original decision boundary.
Off-the-shelf sensor vs. experimental radar -- How much resolution is necessary in automotive radar classification?
Furthermore, the generalization capabilities of both data sets are evaluated and important comparison metrics for automotive radar object detection are discussed.
Toward Optimal Probabilistic Active Learning Using a Bayesian Approach
Gathering labeled data to train well-performing machine learning models is one of the critical challenges in many applications.
Extended Coopetitive Soft Gating Ensemble
This article is about an extension of a recent ensemble method called Coopetitive Soft Gating Ensemble (CSGE) and its application on power forecasting as well as motion primitive forecasting of cyclists.
Emerging Relation Network and Task Embedding for Multi-Task Regression Problems
Results suggest that the ern is beneficial when tasks are only loosely related and the prediction problem is more non-linear.
Iterative Label Improvement: Robust Training by Confidence Based Filtering and Dataset Partitioning
To alleviate this issue, we propose a novel meta training and labelling scheme that is able to use inexpensive unlabelled data by taking advantage of the generalization power of deep neural networks.
Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar
In this work, we depart from visible-wavelength approaches and demonstrate detection, classification, and tracking of hidden objects in large-scale dynamic environments using Doppler radars that can be manufactured at low-cost in series production.
A Multi-Stage Clustering Framework for Automotive Radar Data
The merging process is often implemented in form of a clustering algorithm.
Generative Adversarial Networks for Operational Scenario Planning of Renewable Energy Farms: A Study on Wind and Photovoltaic
In these scenarios, operators examine temporal as well as spatial influences of different energy sources on the grid.
Influences in Forecast Errors for Wind and Photovoltaic Power: A Study on Machine Learning Models
Despite the increasing importance of forecasts of renewable energy, current planning studies only address a general estimate of the forecast quality to be expected and selected forecast horizons.
Radar-based Road User Classification and Novelty Detection with Recurrent Neural Network Ensembles
Radar-based road user classification is an important yet still challenging task towards autonomous driving applications.
Automated Ground Truth Estimation For Automotive Radar Tracking Applications With Portable GNSS And IMU Devices
The reference system allows to much more precisely generate real world radar data distributions of VRUs than compared to conventional methods.
Radar-based Feature Design and Multiclass Classification for Road User Recognition
The classification of individual traffic participants is a complex task, especially for challenging scenarios with multiple road users or under bad weather conditions.
Automated Ground Truth Estimation of Vulnerable Road Users in Automotive Radar Data Using GNSS
Annotating automotive radar data is a difficult task.
Collaborative Interactive Learning -- A clarification of terms and a differentiation from other research fields
The field of collaborative interactive learning (CIL) aims at developing and investigating the technological foundations for a new generation of smart systems that support humans in their everyday life.
Limitations of Assessing Active Learning Performance at Runtime
Hence, it is not possible to reliably estimate the performance of the classification system during learning and it is difficult to decide when the system fulfills the quality requirements (stopping criteria).
Detecting Intentions of Vulnerable Road Users Based on Collective Intelligence
Heterogeneous, open sets of agents (cooperating and interacting vehicles, infrastructure, e. g. cameras and laser scanners, and VRUs equipped with smart devices and body-worn sensors) exchange information forming a multi-modal sensor system with the goal to reliably and robustly detect VRUs and their intentions under consideration of real time requirements and uncertainties.
Quantifying the Influences on Probabilistic Wind Power Forecasts
Therefore, we examine the potential influences with techniques from the field of sensitivity analysis on three different black-box models to obtain insights into differences and similarities of these probabilistic models.
Starting Movement Detection of Cyclists Using Smart Devices
In near future, vulnerable road users (VRUs) such as cyclists and pedestrians will be equipped with smart devices and wearables which are capable to communicate with intelligent vehicles and other traffic participants.
Coopetitive Soft Gating Ensemble
In this article, we propose the Coopetititve Soft Gating Ensemble or CSGE for general machine learning tasks and interwoven systems.
A Multi-Scheme Ensemble Using Coopetitive Soft-Gating With Application to Power Forecasting for Renewable Energy Generation
The proposed algorithm combines the ideas of multiple ensemble paradigms (power forecasting model ensemble, weather forecasting model ensemble, and lagged ensemble) in a hierarchical structure.
Cooperative Starting Movement Detection of Cyclists Using Convolutional Neural Networks and a Boosted Stacking Ensemble
In future, vehicles and other traffic participants will be interconnected and equipped with various types of sensors, allowing for cooperation on different levels, such as situation prediction or intention detection.
Intentions of Vulnerable Road Users - Detection and Forecasting by Means of Machine Learning
Furthermore, the architecture is used to evaluate motion-specific physical models for starting and stopping and video-based pedestrian motion classification.
Highly Automated Learning for Improved Active Safety of Vulnerable Road Users
Highly automated driving requires precise models of traffic participants.
Early Start Intention Detection of Cyclists Using Motion History Images and a Deep Residual Network
The method uses a deep Convolutional Neural Network (CNN) with a residual network architecture (ResNet), which is commonly used in image classification and detection tasks.
Cooperative Tracking of Cyclists Based on Smart Devices and Infrastructure
We show in numerical evaluations on scenes where cyclists are starting or turning right that the cooperation leads to an improvement in both the ability to keep track of a cyclist and the accuracy of the track particularly when it comes to occlusions in the visual system.
Self-Adaptation of Activity Recognition Systems to New Sensors
Traditional activity recognition systems work on the basis of training, taking a fixed set of sensors into account.
Organic Computing in the Spotlight
Organic Computing is an initiative in the field of systems engineering that proposed to make use of concepts such as self-adaptation and self-organisation to increase the robustness of technical systems.
Semi-Supervised Active Learning for Support Vector Machines: A Novel Approach that Exploits Structure Information in Data
An effective approach to reduce these costs is to apply any kind of active learning (AL) methods, as AL controls the training process of a classifier by specific querying individual data points (samples), which are then labeled (e. g., provided with class memberships) by a domain expert.
Variational Bayesian Inference for Hidden Markov Models With Multivariate Gaussian Output Distributions
Hidden Markov Models (HMM) have been used for several years in many time series analysis or pattern recognitions tasks.
Towards Automation of Knowledge Understanding: An Approach for Probabilistic Generative Classifiers
These measures not only support a data miner in evaluating results of a data mining process based on such classifiers.
Detecting Novel Processes with CANDIES -- An Holistic Novelty Detection Technique based on Probabilistic Models
As a consequence, new kinds of samples are observed that require an adaptation of the model.
A New Vision of Collaborative Active Learning
Active learning (AL) is a learning paradigm where an active learner has to train a model (e. g., a classifier) which is in principal trained in a supervised way, but in AL it has to be done by means of a data set with initially unlabeled samples.
The Responsibility Weighted Mahalanobis Kernel for Semi-Supervised Training of Support Vector Machines for Classification
We will see that this kernel outperforms the RBF kernel and other kernels capturing structure in data (such as the LAP kernel in Laplacian SVM) in many applications where partially labeled data are available, i. e., for semi-supervised training of SVM.
