4 papers
PartImageNet++ Dataset: Enhancing Visual Models with High-Quality Part Annotations
Xiao Li, Zilong Liu, Yining Liu +4
To address the scarcity of high-quality part annotations in existing datasets, we introduce PartImageNet++ (PIN++), a dataset that provides detailed part annotations for all catego…
ADBM: Adversarial diffusion bridge model for reliable adversarial purification
Xiao Li, Wenxuan Sun, Huanran Chen +5
Recently Diffusion-based Purification (DiffPure) has been recognized as an effective defense method against adversarial examples. However, we find DiffPure which directly employs t…
PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition
Xiao Li, Yining Liu, Na Dong +2
Deep learning-based object recognition systems can be easily fooled by various adversarial perturbations. One reason for the weak robustness may be that they do not have part-based…
Language-Driven Anchors for Zero-Shot Adversarial Robustness
Xiao Li, Wei Zhang, Yining Liu +3
Deep Neural Networks (DNNs) are known to be susceptible to adversarial attacks. Previous researches mainly focus on improving adversarial robustness in the fully supervised setting…