13 papers
Efficient Bayesian Inference from Noisy Pairwise Comparisons
Till Aczel, Lucas Theis, Roger Wattenhofer
Evaluating generative models is challenging because standard metrics often fail to reflect human preferences. Human evaluations are more reliable but costly and noisy, as participa…
GIC-DLC: Differentiable Logic Circuits for Hardware-Friendly Grayscale Image Compression
Till Aczel, David F. Jenny, Simon Bührer +3
Neural image codecs achieve higher compression ratios than traditional hand-crafted methods such as PNG or JPEG-XL, but often incur substantial computational overhead, limiting the…
Keep It Real: Challenges in Attacking Compression-Based Adversarial Purification
Samuel Räber, Till Aczel, Andreas Plesner +1
Previous work has suggested that preprocessing images through lossy compression can defend against adversarial perturbations, but comprehensive attack evaluations have been lacking…
Virtual Fashion Photo-Shoots: Building a Large-Scale Garment-Lookbook Dataset
Yannick Hauri, Luca A. Lanzendörfer, Till Aczel
Fashion image generation has so far focused on narrow tasks such as virtual try-on, where garments appear in clean studio environments. In contrast, editorial fashion presents garm…
From MNIST to ImageNet: Understanding the Scalability Boundaries of Differentiable Logic Gate Networks
Sven Brändle, Till Aczel, Andreas Plesner +1
Differentiable Logic Gate Networks (DLGNs) are a very fast and energy-efficient alternative to conventional feed-forward networks. With learnable combinations of logical gates, DLG…
The Impact of Scaling Training Data on Adversarial Robustness
Marco Zimmerli, Andreas Plesner, Till Aczel +1
Deep neural networks remain vulnerable to adversarial examples despite advances in architectures and training paradigms. We investigate how training data characteristics affect adv…