DGMamba: Domain Generalization via Generalized State Space Model

arXiv:2404.07794v1 Announce Type: new
Abstract: Domain generalization~(DG) aims at solving distribution shift problems in various scenes. Existing approaches are based on Convolution Neural Networks (CNNs) or Vision Transformers (ViTs), which suffer from limited receptive fields or quadratic complexities issues. Mamba, as an emerging state space model (SSM), possesses superior linear complexity and global receptive fields. Despite this, it can hardly be applied to DG to address distribution shifts, due to the hidden state issues and inappropriate scan mechanisms. In this …

abstract arxiv cnns complexities complexity convolution cs.cv distribution domain fields generalized linear mamba networks neural networks shift space ssm state state space model transformers type via vision vision transformers