8 papers
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…
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…
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…
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…
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…