no code implementations • 1 Mar 2024 • Nikolas Adaloglou, Tim Kaiser, Felix Michels, Markus Kollmann
We present a comprehensive experimental study on image-level conditioning for diffusion models using cluster assignments.
1 code implementation • 31 Mar 2023 • Nikolas Adaloglou, Felix Michels, Hamza Kalisch, Markus Kollmann
We present a general methodology that learns to classify images without labels by leveraging pretrained feature extractors.
Ranked #1 on Image Clustering on CIFAR-10 (using extra training data)
1 code implementation • 10 Mar 2023 • Nikolas Adaloglou, Felix Michels, Tim Kaiser, Markus Kollmann
Intriguingly, we show that (i) PLP outperforms the previous state-of-the-art \citep{ming2022mcm} on all $5$ large-scale benchmarks based on ImageNet, specifically by an average AUROC gain of 3. 4\% using the largest CLIP model (ViT-G), (ii) we show that linear probing outperforms fine-tuning by large margins for CLIP architectures (i. e.
no code implementations • 9 Jul 2021 • Tobias Uelwer, Felix Michels, Oliver De Candido
Our method is able to detect adversarial examples generated by various attacks, and can be easily adopted to a plethora of deep classification models.
1 code implementation • 9 Jun 2019 • Felix Michels, Tobias Uelwer, Eric Upschulte, Stefan Harmeling
This paper extensively evaluates the vulnerability of capsule networks to different adversarial attacks.