Understanding Robustness of Visual State Space Models for Image Classification

arXiv:2403.10935v1 Announce Type: new
Abstract: Visual State Space Model (VMamba) has recently emerged as a promising architecture, exhibiting remarkable performance in various computer vision tasks. However, its robustness has not yet been thoroughly studied. In this paper, we delve into the robustness of this architecture through comprehensive investigations from multiple perspectives. Firstly, we investigate its robustness to adversarial attacks, employing both whole-image and patch-specific adversarial attacks. Results demonstrate superior adversarial robustness compared to Transformer architectures while revealing scalability weaknesses. Secondly, …

abstract architecture arxiv classification computer computer vision cs.cv however image investigations multiple paper performance robustness space state tasks through type understanding vision visual