Adversarial training has become the de-facto standard method for improving the robustness
of models against adversarial examples. However, robust overfitting remains a significant …

Recent years have seen the ever-increasing importance of pre-trained models and their
downstream training in deep learning research and applications. At the same time, the …

We propose the gradient-weighted Object Detector Activation Maps (ODAM), a visualized
explanation technique for interpreting the predictions of object detectors. Utilizing the …

Recently, deep-learning-based models have achieved impressive performance on tasks that
were previously considered to be extremely challenging. However, recent works have …

In safety-critical applications such as medical imaging and autonomous driving, where
decisions have profound implications for patient health and road safety, it is imperative to …

This work addresses the challenge of achieving zero-shot adversarial robustness while
preserving zero-shot generalization in large-scale foundation models, with a focus on the …

We propose the gradient-weighted Object Detector Activation Maps (ODAM), a visual
explanation technique for interpreting the predictions of object detectors. Utilizing the …