ImageNet-100

ImageNet-100 is a subset of the ImageNet dataset that contains 100 classes and is used to evaluate the performance of image classifiers, particularly in the context of adversarial robustness against gradient-based attacks.

Papers using ImageNet-100 (3)

Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization2026Checkerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning Budget2026TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks2025