Self-Attention Technology in Image Segmentation

Although the traditional Convolutional neural network is applied to image segmentation successfully, it has some limitations. That's the context information of the long-range on the image is not well captured. With the success of the introduction of self-attentional mechanisms in the field of natural language processing (NLP), people have tried to introduce the attention mechanism in the field of computer vision. It turns out that self-attention can really solve this long-range dependency problem. This paper is a summary on the application of self-attention to image segmentation in the past two years. And we think about whether the self-attention module in this field can replace convolution operation in the future. The answer to this review is yes, so it is recommended that the focus of future research be on the self-attention module.