What Makes the Convolutions of Robust Vision Models Special?

Understanding adversarial robustness through the lens of convolutional filters

Based on collaborative work with Janis Keuper.

Symbolic visualization of the first convolution filters of each layer in a ResNet-18 trained on CIFAR-10. Image by the authors.

Deep learning has had a significant impact on computer vision. It has enabled computers to automatically learn high-level features from data, and has been used to develop models that can outperform traditional approaches on a variety of tasks such as object recognition, image classification, …

computer vision convolutional-network deep learning machine learning robustness vision