Deep Learning is the most widely used tool in the contemporary field of computer vision. Its
ability to accurately solve complex problems is employed in vision research to learn deep …

It has been recognized that the data generated by the denoising diffusion probabilistic
model (DDPM) improves adversarial training. After two years of rapid development in …

Prevalent semantic segmentation solutions, despite their different network designs (FCN
based or attention based) and mask decoding strategies (parametric softmax based or pixel …

Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved
great success and become a milestone in the field of artificial intelligence (AI). Owing to …

Current semantic segmentation methods focus only on mining" local" context, ie,
dependencies between pixels within individual images, by context-aggregation modules …

As a research community, we are still lacking a systematic understanding of the progress on
adversarial robustness which often makes it hard to identify the most promising ideas in …

The field of defense strategies against adversarial attacks has significantly grown over the
last years, but progress is hampered as the evaluation of adversarial defenses is often …

Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to
adversarial examples. We find, however, that typical adaptive evaluations are incomplete …

We devise deep nearest centroids (DNC), a conceptually elegant yet surprisingly effective
network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most …

The evaluation of robustness against adversarial manipulation of neural networks-based
classifiers is mainly tested with empirical attacks as methods for the exact computation, even …