<ul><li>Researchers propose an approach to enhance the robustness of vision transformers (ViTs) inspired by the concept of nullspace from linear algebra.</li><li>The investigation focuses on whether ViTs can exhibit resilience to input variations akin to the nullspace property in linear mappings.</li><li>The researchers extend the notion of nullspace to nonlinear settings and demonstrate the synthesis of approximate nullspace elements for ViT's encoder blocks through optimization.</li><li>A finetuning strategy is proposed for ViTs by augmenting the training data with synthesized approximate nullspace noise, leading to improved robustness.</li></ul>

Approximate Nullspace Augmented Finetuning for Robust Vision Transformers

Discover more