176 citations · 336 across the 51 of their papers we have counts for
40 papers · 1 filter
LAION-Mobile: Evaluating Deepfake Detectors On One Million Smartphone Photos
Achim von Stryk, Janis Keuper
Most Deepfake detectors report near-perfect AUC scores on their reference benchmarks. However, a recent ICML position paper argues that these evaluations collectively neglect the i…
Deepfakes: we need to re-think the concept of "real" images
Janis Keuper, Margret Keuper
The wide availability and low usability barrier of modern image generation models has triggered the reasonable fear of criminal misconduct and negative social implications. The mac…
How Do Training Methods Influence the Utilization of Vision Models?
Paul Gavrikov, Shashank Agnihotri, Margret Keuper +1
Not all learnable parameters (e.g., weights) contribute equally to a neural network's decision function. In fact, entire layers' parameters can sometimes be reset to random values…
Can Visual Language Models Replace OCR-Based Visual Question Answering Pipelines in Production? A Case Study in Retail
Bianca Lamm, Janis Keuper
Most production-level deployments for Visual Question Answering (VQA) tasks are still build as processing pipelines of independent steps including image pre-processing, object- and…
Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration
Shashank Agnihotri, Julia Grabinski, Janis Keuper +1
Image restoration networks are usually comprised of an encoder and a decoder, responsible for aggregating image content from noisy, distorted data and to restore clean, undistorted…
Ambiguous Annotations: When is a Pedestrian not a Pedestrian?
Luisa Schwirten, Jannes Scholz, Daniel Kondermann +1
Datasets labelled by human annotators are widely used in the training and testing of machine learning models. In recent years, researchers are increasingly paying attention to labe…
Can Biases in ImageNet Models Explain Generalization?
Paul Gavrikov, Janis Keuper
The robust generalization of models to rare, in-distribution (ID) samples drawn from the long tail of the training distribution and to out-of-training-distribution (OOD) samples is…
Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets
Patrick Grommelt, Louis Weiss, Franz-Josef Pfreundt +1
The widespread adoption of generative image models has highlighted the urgent need to detect artificial content, which is a crucial step in combating widespread manipulation and mi…
Can We Talk Models Into Seeing the World Differently?
Paul Gavrikov, Jovita Lukasik, Steffen Jung +4
Unlike traditional vision-only models, vision language models (VLMs) offer an intuitive way to access visual content through language prompting by combining a large language model…
Adversarial Examples are Misaligned in Diffusion Model Manifolds
Peter Lorenz, Ricard Durall, Janis Keuper
In recent years, diffusion models (DMs) have drawn significant attention for their success in approximating data distributions, yielding state-of-the-art generative results. Nevert…
Retail-786k: a Large-Scale Dataset for Visual Entity Matching
Bianca Lamm, Janis Keuper
Entity Matching (EM) defines the task of learning to group objects by transferring semantic concepts from example groups (=entities) to unseen data. Despite the general availabilit…
Don't Look into the Sun: Adversarial Solarization Attacks on Image Classifiers
Paul Gavrikov, Janis Keuper
Assessing the robustness of deep neural networks against out-of-distribution inputs is crucial, especially in safety-critical domains like autonomous driving, but also in safety sy…
On the Interplay of Convolutional Padding and Adversarial Robustness
Paul Gavrikov, Janis Keuper
It is common practice to apply padding prior to convolution operations to preserve the resolution of feature-maps in Convolutional Neural Networks (CNN). While many alternatives ex…
As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain
Julia Grabinski, Janis Keuper, Margret Keuper
Recent work in neural networks for image classification has seen a strong tendency towards increasing the spatial context. Whether achieved through large convolution kernels or sel…
Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
Julia Grabinski, Steffen Jung, Janis Keuper +1
Convolutional Neural Networks (CNNs) are successful in various computer vision tasks. From an image and signal processing point of view, this success is counter-intuitive, as the i…
Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality
Peter Lorenz, Ricard Durall, Janis Keuper
Diffusion models recently have been successfully applied for the visual synthesis of strikingly realistic appearing images. This raises strong concerns about their potential for ma…
Fine-Grained Product Classification on Leaflet Advertisements
Daniel Ladwig, Bianca Lamm, Janis Keuper
In this paper, we describe a first publicly available fine-grained product recognition dataset based on leaflet images. Using advertisement leaflets, collected over several years f…
An Extended Study of Human-like Behavior under Adversarial Training
Paul Gavrikov, Janis Keuper, Margret Keuper
Neural networks have a number of shortcomings. Amongst the severest ones is the sensitivity to distribution shifts which allows models to be easily fooled into wrong predictions by…
The Power of Linear Combinations: Learning with Random Convolutions
Paul Gavrikov, Janis Keuper
Following the traditional paradigm of convolutional neural networks (CNNs), modern CNNs manage to keep pace with more recent, for example transformer-based, models by not only incr…
Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection
Peter Lorenz, Margret Keuper, Janis Keuper
Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks. However, current CNN approaches largely remain vulnerable against adversarial per…
Robust Models are less Over-Confident
Julia Grabinski, Paul Gavrikov, Janis Keuper +1
Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental c…
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
Paul Gavrikov, Janis Keuper
Currently, many theoretical as well as practically relevant questions towards the transferability and robustness of Convolutional Neural Networks (CNNs) remain unsolved. While ongo…
Adversarial Robustness through the Lens of Convolutional Filters
Paul Gavrikov, Janis Keuper
Deep learning models are intrinsically sensitive to distribution shifts in the input data. In particular, small, barely perceivable perturbations to the input data can force models…
FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting
Julia Grabinski, Steffen Jung, Janis Keuper +1
Over the last years, Convolutional Neural Networks (CNNs) have been the dominating neural architecture in a wide range of computer vision tasks. From an image and signal processing…