41 citations · 88 across the 8 of their papers we have counts for
10 papers
DASH: Detection and Assessment of Systematic Hallucinations of VLMs
Maximilian Augustin, Yannic Neuhaus, Matthias Hein
Vision-language models (VLMs) are prone to object hallucinations, where they erroneously indicate the presenceof certain objects in an image. Existing benchmarks quantify hallucina…
DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations
Maximilian Augustin, Yannic Neuhaus, Matthias Hein
While deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features, call into question how relia…
Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet
Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko +1
Benchmark performance of deep learning classifiers alone is not a reliable predictor for the performance of a deployed model. In particular, if the image classifier has picked up s…
Diffusion Visual Counterfactual Explanations
Maximilian Augustin, Valentyn Boreiko, Francesco Croce +1
Visual Counterfactual Explanations (VCEs) are an important tool to understand the decisions of an image classifier. They are 'small' but 'realistic' semantic changes of the image c…
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities
Julian Bitterwolf, Alexander Meinke, Maximilian Augustin +1
It is an important problem in trustworthy machine learning to recognize out-of-distribution (OOD) inputs which are inputs unrelated to the in-distribution task. Many out-of-distrib…
Sparse Visual Counterfactual Explanations in Image Space
Valentyn Boreiko, Maximilian Augustin, Francesco Croce +2
Visual counterfactual explanations (VCEs) in image space are an important tool to understand decisions of image classifiers as they show under which changes of the image the decisi…
Out-distribution aware Self-training in an Open World Setting
Maximilian Augustin, Matthias Hein
Deep Learning heavily depends on large labeled datasets which limits further improvements. While unlabeled data is available in large amounts, in particular in image recognition, i…
Adversarial Robustness on In- and Out-Distribution Improves Explainability
Maximilian Augustin, Alexander Meinke, Matthias Hein
Neural networks have led to major improvements in image classification but suffer from being non-robust to adversarial changes, unreliable uncertainty estimates on out-distribution…
MLCapsule: Guarded Offline Deployment of Machine Learning as a Service
Lucjan Hanzlik, Yang Zhang, Kathrin Grosse +4
With the widespread use of machine learning (ML) techniques, ML as a service has become increasingly popular. In this setting, an ML model resides on a server and users can query i…
Towards Reverse-Engineering Black-Box Neural Networks
Seong Joon Oh, Max Augustin, Bernt Schiele +1
Many deployed learned models are black boxes: given input, returns output. Internal information about the model, such as the architecture, optimisation procedure, or training data,…