Mansformer: Efficient Transformer of Mixed Attention for Image Deblurring and Beyond

arXiv:2404.06135v1 Announce Type: new
Abstract: Transformer has made an enormous success in natural language processing and high-level vision over the past few years. However, the complexity of self-attention is quadratic to the image size, which makes it infeasible for high-resolution vision tasks. In this paper, we propose the Mansformer, a Transformer of mixed attention that combines multiple self-attentions, gate, and multi-layer perceptions (MLPs), to explore and employ more possibilities of self-attention. Taking efficiency into account, we design four kinds of …

abstract arxiv attention beyond complexity cs.cv however image language language processing mixed natural natural language natural language processing paper processing resolution self-attention success tasks transformer type vision