Robust and Generalizable Visual Representation Learning via Random Convolutions

Understand

While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust.

• In this work, we show that the robustness of neural networks can be greatly improved through the use of random convolutions as data augmentation.
• Random convolutions are approximately shape-preserving and may distort local textures.
• Intuitively, randomized convolutions create an infinite number of new domains with similar global shapes but random local textures.