119 citations · 845 across the 65 of their papers we have counts for
25 papers · 1 filter
DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion
Marcel Lamott, Saifullah Saifullah, Nauman Riaz +11
Effective document intelligence models rely on large amounts of annotated training data. However, procuring sufficient and high-quality data poses significant challenges due to the…
The Sound of Death: Deep Learning Reveals Vascular Damage from Carotid Ultrasound
Christoph Balada, Aida Romano-Martinez, Payal Varshney +10
Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, yet early risk detection is often limited by available diagnostics. Carotid ultrasound, a non-invasi…
FREQuency ATTribution: benchmarking frequency-based occlusion for time series data
Dominique Mercier, Andreas Dengel, Sheraz Ahmed
Deep neural networks are among the most successful algorithms in terms of performance and scalability across different domains. However, since these networks are black boxes, their…
VAEneu: A New Avenue for VAE Application on Probabilistic Forecasting
Alireza Koochali, Ensiye Tahaei, Andreas Dengel +1
This paper presents VAEneu, an innovative autoregressive method for multistep ahead univariate probabilistic time series forecasting. We employ the conditional VAE framework and op…
Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discovery
Payal Varshney, Adriano Lucieri, Christoph Balada +2
Trustworthiness is a major prerequisite for the safe application of opaque deep learning models in high-stakes domains like medicine. Understanding the decision-making process not…
Class Conditional Time Series Generation with Structured Noise Space GAN
Hamidreza Gholamrezaei, Alireza Koochali, Andreas Dengel +1
This paper introduces Structured Noise Space GAN (SNS-GAN), a novel approach in the field of generative modeling specifically tailored for class-conditional generation in both imag…
From Private to Public: Benchmarking GANs in the Context of Private Time Series Classification
Dominique Mercier, Andreas Dengel, Sheraz Ahmed
Deep learning has proven to be successful in various domains and for different tasks. However, when it comes to private data several restrictions are making it difficult to use dee…
A Bayesian Generative Adversarial Network (GAN) to Generate Synthetic Time-Series Data, Application in Combined Sewer Flow Prediction
Amin E. Bakhshipour, Alireza Koochali, Ulrich Dittmer +3
Despite various breakthroughs in machine learning and data analysis techniques for improving smart operation and management of urban water infrastructures, some key limitations obs…
Privacy Meets Explainability: A Comprehensive Impact Benchmark
Saifullah Saifullah, Dominique Mercier, Adriano Lucieri +2
Since the mid-10s, the era of Deep Learning (DL) has continued to this day, bringing forth new superlatives and innovations each year. Nevertheless, the speed with which these inno…
Quantifying Quality of Class-Conditional Generative Models in Time-Series Domain
Alireza Koochali, Maria Walch, Sankrutyayan Thota +3
Generative models are designed to address the data scarcity problem. Even with the exploding amount of data, due to computational advancements, some applications (e.g., health care…
KENN: Enhancing Deep Neural Networks by Leveraging Knowledge for Time Series Forecasting
Muhammad Ali Chattha, Ludger van Elst, Muhammad Imran Malik +2
End-to-end data-driven machine learning methods often have exuberant requirements in terms of quality and quantity of training data which are often impractical to fulfill in real-w…
TimeREISE: Time-series Randomized Evolving Input Sample Explanation
Dominique Mercier, Andreas Dengel, Sheraz Ahmed
Deep neural networks are one of the most successful classifiers across different domains. However, due to their limitations concerning interpretability their use is limited in safe…
Random Noise vs State-of-the-Art Probabilistic Forecasting Methods : A Case Study on CRPS-Sum Discrimination Ability
Alireza Koochali, Peter Schichtel, Andreas Dengel +1
The recent developments in the machine learning domain have enabled the development of complex multivariate probabilistic forecasting models. Therefore, it is pivotal to have a pre…
Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification
Dominique Mercier, Adriano Lucieri, Mohsin Munir +2
With the advent of machine learning in applications of critical infrastructure such as healthcare and energy, privacy is a growing concern in the minds of stakeholders. It is pivot…
PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification
Dominique Mercier, Andreas Dengel, Sheraz Ahmed
The classification of time-series data is pivotal for streaming data and comes with many challenges. Although the amount of publicly available datasets increases rapidly, deep neur…
Benchmarking adversarial attacks and defenses for time-series data
Shoaib Ahmed Siddiqui, Andreas Dengel, Sheraz Ahmed
The adversarial vulnerability of deep networks has spurred the interest of researchers worldwide. Unsurprisingly, like images, adversarial examples also translate to time-series da…
Interpreting Deep Models through the Lens of Data
Dominique Mercier, Shoaib Ahmed Siddiqui, Andreas Dengel +1
Identification of input data points relevant for the classifier (i.e. serve as the support vector) has recently spurred the interest of researchers for both interpretability as wel…
On Interpretability of Deep Learning based Skin Lesion Classifiers using Concept Activation Vectors
Adriano Lucieri, Muhammad Naseer Bajwa, Stephan Alexander Braun +3
Deep learning based medical image classifiers have shown remarkable prowess in various application areas like ophthalmology, dermatology, pathology, and radiology. However, the acc…
Explaining AI-based Decision Support Systems using Concept Localization Maps
Adriano Lucieri, Muhammad Naseer Bajwa, Andreas Dengel +1
Human-centric explainability of AI-based Decision Support Systems (DSS) using visual input modalities is directly related to reliability and practicality of such algorithms. An oth…
If You Like It, GAN It. Probabilistic Multivariate Times Series Forecast With GAN
Alireza Koochali, Andreas Dengel, Sheraz Ahmed
The contribution of this paper is two-fold. First, we present ProbCast - a novel probabilistic model for multivariate time-series forecasting. We employ a conditional GAN framework…
TSInsight: A local-global attribution framework for interpretability in time-series data
Shoaib Ahmed Siddiqui, Dominique Mercier, Andreas Dengel +1
With the rise in the employment of deep learning methods in safety-critical scenarios, interpretability is more essential than ever before. Although many different directions regar…
TSXplain: Demystification of DNN Decisions for Time-Series using Natural Language and Statistical Features
Mohsin Munir, Shoaib Ahmed Siddiqui, Ferdinand Küsters +3
Neural networks (NN) are considered as black-boxes due to the lack of explainability and transparency of their decisions. This significantly hampers their deployment in environment…
Probabilistic Forecasting of Sensory Data with Generative Adversarial Networks - ForGAN
Alireza Koochali, Peter Schichtel, Sheraz Ahmed +1
Time series forecasting is one of the challenging problems for humankind. Traditional forecasting methods using mean regression models have severe shortcomings in reflecting real-w…
KINN: Incorporating Expert Knowledge in Neural Networks
Muhammad Ali Chattha, Shoaib Ahmed Siddiqui, Muhammad Imran Malik +3
The promise of ANNs to automatically discover and extract useful features/patterns from data without dwelling on domain expertise although seems highly promising but comes at the c…