Andreas Dengel

Deutsches Forschungszentrum für Künstliche Intelligenz | DFKI · Smart Data & Knowledge Services

Diffusion models have enabled the generation of high-quality images with a strong focus on realism and textual fidelity. Yet, large-scale text-to-image models, such as Stable Diffusion, struggle to generate images where foreground objects are placed over a chroma key background, limiting their ability to separate foreground and background elements...

Diffusion models, known for their generative capabilities, have recently shown unexpected potential in image classification tasks by using Bayes' theorem. However, most diffusion classifiers require evaluating all class labels for a single classification, leading to significant computational costs that can hinder their application in large-scale sc...

Large-scale, pre-trained Text-to-Image (T2I) diffusion models have gained significant popularity in image generation tasks and have shown unexpected potential in image Super-Resolution (SR). However, most existing T2I diffusion models are trained with a resolution limit of 512x512, making scaling beyond this resolution an unresolved but necessary c...

Dataset distillation has gained significant interest in recent years, yet existing approaches typically distill from the entire dataset, potentially including non-beneficial samples. We introduce a novel "Prune First, Distill After" framework that systematically prunes datasets via loss-based sampling prior to distillation. By leveraging pruning be...

Transformer-based Super-Resolution (SR) models have recently advanced image reconstruction quality, yet challenges remain due to computational complexity and an over-reliance on large patch sizes, which constrain fine-grained detail enhancement. In this work, we propose TaylorIR to address these limitations by utilizing a patch size of 1x1, enablin...

Diffusion models (DMs) have disrupted the image super-resolution (SR) field and further closed the gap between image quality and human perceptual preferences. They are easy to train and can produce very high-quality samples that exceed the realism of those produced by previous generative methods. Despite their promising results, they also come with...

Autonomous driving systems require a quick and robust perception of the nearby environment to carry out their routines effectively. With the aim to avoid collisions and drive safely, autonomous driving systems rely heavily on object detection. However, 2D object detections alone are insufficient; more information, such as relative velocity and dist...

from "Impact Assessment of Missing Data in Model Predictions for Earth Observation Applications"

from "Increasing the Robustness of Model Predictions to Missing Sensors in Earth Observation"

Understanding the correlation between EEG features and cognitive tasks is crucial for elucidating brain function. Brain activity synchronizes during speaking and listening tasks. However, it is challenging to estimate task-dependent brain activity characteristics with methods with low spatial resolution but high temporal resolution, such as EEG, ra...

Understanding the correlation between EEG features and cognitive tasks is crucial for elucidating brain function. Brain activity synchronizes during speaking and listening tasks. However, it is challenging to estimate task-dependent brain activity characteristics with methods with low spatial resolution but high temporal resolution, such as EEG, ra...

In image Super-Resolution (SR), relying on large datasets for training is a double-edged sword. While offering rich training material , they also demand substantial computational and storage resources. In this work, we analyze dataset pruning to solve these challenges. We introduce a novel approach that reduces a dataset to a core-set of training s...

In recent years, deep learning-based image compression, particularly through generative models, has emerged as a pivotal area of research. Despite significant advancements, challenges such as diminished sharpness and quality in reconstructed images, learning inefficiencies due to mode collapse, and data loss during transmission persist. To address...

In recent years, deep learning-based image compression , particularly through generative models, has emerged as a pivotal area of research. Despite significant advancements, challenges such as diminished sharpness and quality in reconstructed images, learning inefficiencies due to mode collapse, and data loss during transmission persist. To address...

The process of cyber mapping gives insights in relationships among financial entities and service providers. Centered around the outsourcing practices of companies within fund prospectuses in Germany, we introduce a dataset specifically designed for named entity recognition and relation extraction tasks. The labeling process on 948 sentences was ca...

We present Q-Seg, a novel unsupervised image segmentation method based on quantum annealing, tailored for existing quantum hardware. We formulate the pixel- wise segmentation problem, which assimilates spectral and spatial information of the image, as a graph-cut optimization task. Our method efficiently leverages the interconnected qubit topology...

Current publicly available knowledge work data collections lack diversity, extensive annotations, and contextual information about the users and their documents. These issues hinder objective and comparable data-driven evaluations and optimizations of knowledge work assistance systems. Due to the considerable resources needed to collect such data i...

Background: Decisions on the best available treatment in clinical oncology are based on expert opinions in multidisciplinary cancer conferences (MCC). For this purpose, artificial intelligence (AI) could increase evidence-based treatment in clinical oncology as assistance system to give an additional treatment recommendation in MCC. Here, we presen...

The availability of temporal geospatial data in multiple modalities has been extensively leveraged to enhance the performance of machine learning models. While efforts on the design of adequate model architectures are approaching a level of saturation, focusing on a data-centric perspective can complement these efforts to achieve further enhancemen...

Obtaining annotated table structure data for complex tables is a challenging task due to the inherent diversity and complexity of real-world document layouts. The scarcity of publicly available datasets with comprehensive annotations for intricate table structures hinders the development and evaluation of models designed for such scenarios. This re...

Capturing pupil diameter is essential for assessing psychological and physiological states such as stress levels and cognitive load. However, the low resolution of images in eye datasets often hampers precise measurement. This study evaluates the impact of various upscaling methods, ranging from bicubic interpolation to advanced super-resolution, o...

The increasing number of Low Earth Orbit (LEO) satellites, driven by lower manufacturing and launch costs, is proving invaluable for Earth observation missions and low-latency internet connectivity. However, as the number of satellites increases, the number of communication links to maintain also rises, making the management of this vast network in...

The emergence of federated learning (FL) presents a promising approach to leverage decentralized data while preserving privacy. Furthermore, the combination of FL and anomaly detection is particularly compelling because it allows for detecting rare and critical anomalies (usually also rare in locally gathered data) in sensitive data from multiple s...

Der vorliegende Beitrag beschäftigt sich mit den unterschiedlichen Anwendungsbereichen der Künstlichen Intelligenz in der Onkologie. Der Schwerpunkt liegt hierbei auf den Herausforderungen in dem technisch noch vergleichsweisen neuen Anwendungsbereich der medizinischen Therapieempfehlung. In den vergangenen Jahren wurden bereits diverse Anwendungen...

Protein solubility prediction is useful for the careful selection of highly effective candidate proteins for drug development. In recombinant proteins synthesis, solubility prediction is valuable for optimizing key protein characteristics, including stability, functionality, and ease of purification. It contains valuable information about potential...

In this study, we introduce StylusAI, a novel architecture leveraging diffusion models in the domain of handwriting style generation. StylusAI is specifically designed to adapt and integrate the stylistic nuances of one language's handwriting into another, particularly focusing on blending English handwriting styles into the context of the German w...

Generating high-resolution images with generative models has recently been made widely accessible by leveraging diffusion models pre-trained on large-scale datasets. Various techniques, such as MultiDiffusion and SyncDiffusion, have further pushed image generation beyond training resolutions, i.e., from square images to panorama, by merging multipl...

Multi-sensor ML models for EO aim to enhance prediction accuracy by integrating data from various sources. However, the presence of missing data poses a significant challenge, particularly in non-persistent sensors that can be affected by external factors. Existing literature has explored strategies like temporal dropout and sensor-invariant models...

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 deep learning approaches in these application fields. Recent approaches try to generate data privately instead of applying a privacy-preserving mechanism directly, on top o...

Generative AI has introduced significant concerns about how people interact with information in society, particularly regarding the potential harm caused by fake news. To address this issue, it is critical to understand how people perceive fake news and how their information literacy can be improved. Our research tackles two key questions: "Can we...

Online lecture is one of the technology-wise challenges in the education field. It provides the advantage of encouraging anyone to join from worldwide. However, understanding students' concentration in remote is one of the difficulties. In this paper, we evaluate multimodal sensors for estimating students' concentration levels during online video l...

In this work, we introduce EyeDentify, a dataset specifically designed for pupil diameter estimation based on webcam images. EyeDentify addresses the lack of available datasets for pupil diameter estimation, a crucial domain for understanding physiological and psychological states traditionally dominated by highly specialized sensor systems such as...

Cellular imaging plays a pivotal role in understanding various biological processes and diseases, making accurate cell segmenta-tion indispensable for many biomedical applications. However, traditional methods for cell segmentation often rely on manual annotation, which is labor-intensive and time-consuming. Deep learning-based approaches for cell...

Cells play a fundamental role in sustaining life by performing numerous functions crucial for the survival of living organisms. The detection of cells holds paramount importance in the validation and analysis of biological hypotheses, as it offers valuable insights into the behavior, function, diagnosis, and treatment of diseases. By accurately det...

Microscopic imaging plays a pivotal role in various fields of science and medicine, offering invaluable insights into the intricate world of cellular biology. At the heart of this endeavor lies the need for accurate identification and characterization of individual cells within these images. Deep learning-based cell segmentation, which involves del...

Crop yield forecasting plays a significant role in addressing growing concerns about food security and guiding decision-making for policymakers and farmers. When deep learning is employed, understanding the learning and decision-making processes of the models, as well as their interaction with the input data, is crucial for establishing trust in th...

Vegetation indices allow to efficiently monitor vegetation growth and agricultural activities. Previous generations of satellites were capturing a limited number of spectral bands, and a few expert-designed vegetation indices were sufficient to harness their potential. New generations of multi- and hyperspectral satellites can however capture addit...

Deep learning (DL) has revolutionized the field of document image analysis, showcasing superhuman performance across a diverse set of tasks. However, the inherent black-box nature of deep learning models still presents a significant challenge to their safe and robust deployment in industry. Regrettably, while a plethora of research has been dedicat...

Since the advent of deep learning (DL), the field has witnessed a continuous stream of innovations. However, the translation of these advancements into practical applications has not kept pace, particularly in safety-critical domains where artificial intelligence (AI) must meet stringent regulatory and ethical standards. This is underscored by the...

Survival prediction integrates patient-specific molecular information and clinical signatures to forecast the anticipated time of an event, such as recurrence, death, or disease progression. Survival prediction proves valuable in guiding treatment decisions, optimizing resource allocation, and interventions of precision medicine. The wide range of...

from "A Comparative Assessment of Multi-View Fusion Learning For Crop Classification"

Model interpretability and robustness are becoming increasingly critical today for the safe and practical deployment of deep learning (DL) models in industrial settings. As DL-backed automated document processing systems become increasingly common in business workflows, there is a pressing need today to enhance interpretability and robustness for t...

Artificial intelligence (AI) promises to be the next revolutionary step in modern society. Yet, its role in all fields of industry and science need to be determined. One very promising field is represented by AI‐based decision‐making tools in clinical oncology leading to more comprehensive, personalized therapy approaches. In this review, the autho...

As data-driven AI systems become increasingly integrated into industry, concerns have recently arisen regarding potential privacy breaches and the inadvertent leakage of sensitive user data through the exploitation of these systems. In this paper, we explore the intersection of data privacy and AI-powered document analysis systems, presenting a com...

In image Super-Resolution (SR), relying on large datasets for training is a double-edged sword. While offering rich training material, they also demand substantial computational and storage resources. In this work, we analyze dataset pruning as a solution to these challenges. We introduce a novel approach that reduces a dataset to a core-set of tra...

Traditional blind image SR methods need to model real-world degradations precisely. Consequently, current research struggles with this dilemma by assuming idealized degradations, which leads to limited applicability to actual user data. Moreover, the ideal scenario-training models on data from the targeted user base-presents significant privacy con...

Since the launch of the Sentinel-2 (S2) satellites, many ML models have used the data for diverse applications. The scene classification layer (SCL) inside the S2 product provides rich information for training, such as filtering images with high cloud coverage. However, there is more potential in this. We propose a technique to assess the clean opt...

Quantum computing is expected to transform a range of computational tasks beyond the reach of classical algorithms. In this work, we examine the application of variational quantum algorithms (VQAs) for unsupervised image segmentation to partition images into separate semantic regions. Specifically, we formulate the task as a graph cut optimization...

Gaze estimation is an important factor in human activity and behavior recognition. The technology is used in numerous applications such as human-computer interaction, driver monitoring systems, and surveillance. Gaze estimation can be achieved using different technologies such as wearable devices or cameras. Estimating gaze using a webcam can indee...

Long extrachromosomal circular DNA (leccDNA) regulates several biological processes such as genomic instability, gene amplification, and oncogenesis. The identification of leccDNA holds significant importance to investigate its potential associations with cancer, autoimmune, cardiovascular, and neurological diseases. In addition, understanding thes...

We present ObjBlur, a novel curriculum learning approach to improve layout-to-image generation models, where the task is to produce realistic images from layouts composed of boxes and labels. Our method is based on progressive object-level blurring, which effectively stabilizes training and enhances the quality of generated images. This curriculum...