Search Results for author:
Found 11 papers, 10 papers with code
Can Biases in ImageNet Models Explain Generalization?
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 one of the major challenges of current deep learning methods.
Are Vision Language Models Texture or Shape Biased and Can We Steer Them?
If text does indeed influence visual biases, this suggests that we may be able to steer visual biases not just through visual input but also through language: a hypothesis that we confirm through extensive experiments.
Don't Look into the Sun: Adversarial Solarization Attacks on Image Classifiers
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 systems where malicious actors can digitally alter inputs to circumvent safety guards.
On the Interplay of Convolutional Padding and Adversarial Robustness
It is common practice to apply padding prior to convolution operations to preserve the resolution of feature-maps in Convolutional Neural Networks (CNN).
An Extended Study of Human-like Behavior under Adversarial Training
Adversarial training poses a partial solution to address this issue by training models on worst-case perturbations.
The Power of Linear Combinations: Learning with Random Convolutions
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 increasing model depth and width but also the kernel size.
Does Medical Imaging learn different Convolution Filters?
However, among the studied image domains, medical imaging models appeared to show significant outliers through "spikey" distributions, and, therefore, learn clusters of highly specific filters different from other domains.
Robust Models are less Over-Confident
Further, our analysis of robust models shows that not only AT but also the model's building blocks (like activation functions and pooling) have a strong influence on the models' prediction confidences.
Adversarial Robustness through the Lens of Convolutional Filters
Deep learning models are intrinsically sensitive to distribution shifts in the input data.
CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters
In a first use case of the proposed dataset, we can show highly relevant properties of many publicly available pre-trained models for practical applications: I) We analyze distribution shifts (or the lack thereof) between trained filters along different axes of meta-parameters, like visual category of the dataset, task, architecture, or layer depth.
Ranked #7 on
Image Classification
on Fashion-MNIST
An Empirical Investigation of Model-to-Model Distribution Shifts in Trained Convolutional Filters
We argue, that the observed properties are a valuable source for further investigation into a better understanding of the impact of shifts in the input data to the generalization abilities of CNN models and novel methods for more robust transfer-learning in this domain.
