ModelVision Transformer Base/16

ViT-B/16

The base version of the Vision Transformer, which splits images into 16x16-pixel patches and converts the image into a sequence fed to a Transformer encoder for image classification.

Timeline (last 90 days)

Oct 14

The paper tested GCD on CIFAR-10 and ImageNet, covering three architectures, ResNet-18, ResNet-50, and ViT-B/16, and evaluated four mainstream attack methods.

Unverified50%

All Facts (1)

Unverified

The paper tested GCD on CIFAR-10 and ImageNet, covering three architectures, ResNet-18, ResNet-50, and ViT-B/16, and evaluated four mainstream attack methods.

50%

Source Articles

Gradient Confusion Defense: Defeating Black-Box Query Attacks Without RetrainingOct 14