Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinement

arXiv:2401.01750v2 Announce Type: replace
Abstract: The attention mechanism has been proven effective on various visual tasks in recent years. In the semantic segmentation task, the attention mechanism is applied in various methods, including the case of both Convolution Neural Networks (CNN) and Vision Transformer (ViT) as backbones. However, we observe that the attention mechanism is vulnerable to patch-based adversarial attacks. Through the analysis of the effective receptive field, we attribute it to the fact that the wide receptive field brought …

abstract arxiv attention case cnn convolution cs.cv however networks neural networks observe robust segmentation semantic tasks transformer type via vision visual vit