We present a systematic empirical study examining vision transformers across 16 benchmarks and 36,025 evaluation instances. Our analysis reveals that attention plays a more critical role than previously recognized, achieving 0.
We present a systematic empirical study examining vision transformers across 26 benchmarks and 14,511 evaluation instances. Our analysis reveals that patch size plays a more critical role than previously recognized, achieving 0.
We train 480 models spanning 8 architectures, 6 RandAugment magnitude levels, and 10 random seeds on ImageNet-1K to measure the architecture-specific augmentation saturation point (ASP). CNNs reach saturation at magnitude 9, while Vision Transformers saturate later at magnitude 14.
Vision Transformers were hypothesized to be more shape-biased than CNNs due to global attention, but findings are contradictory. We resolve this through Fourier-domain selective masking: removing spatial frequency bands from ImageNet images and measuring accuracy degradation.
Vision Transformers (ViTs) have demonstrated remarkable performance across computer vision tasks, yet their robustness properties against adversarial perturbations remain insufficiently understood. In this work, we present a systematic analysis of how the self-attention mechanism in ViTs provides a natural defense against adversarial attacks.