Adversarial Training (AT), which is commonly accepted as one of the most effective
approaches defending against adversarial examples, can largely harm the standard …

Image perturbation technique is widely used to generate adversarial examples to attack
networks, greatly decreasing the performance of networks. Unlike the existing works, in this …

We propose a conceptually simple and lightweight framework for improving the robustness
of vision models through the combination of knowledge distillation and data augmentation …

Large-batch training has become a commonly used technique when training neural
networks with a large number of GPU/TPU processors. As batch size increases, stochastic …

Deep neural networks have achieved remarkable success in a variety of computer vision
applications. However, there is a problem of degrading accuracy when the data distribution …

Abstract Recently, Adversarial Propagation (AdvProp) improves the standard accuracy of a
trained model on clean samples. However, the training speed of AdvProp is much slower …

Distribution shifts, which often occur in the real world, degrade the accuracy of deep learning
systems, and thus improving robustness to distribution shifts is essential for practical …

Deep neural networks (DNNs) struggle to generalize to out-of-distribution domains that are
different from those in training despite their impressive performance. In practical …

Deep Metric Learning (DML) is a prominent field in machine learning with extensive
practical applications that concentrate on learning visual similarities. It is known that inputs …

Recently, Pyramid Adversarial training (Herrmann et al., 2022) has been shown to be very
effective for improving clean accuracy and distribution-shift robustness of vision …