The transformer-based semantic segmentation approaches, which divide the image into different regions by sliding windows and model the relation inside each window, have achieved outstanding success.

In the last decade, convolutional neural networks (CNNs) have been the go-to architecture in computer vision, owing to their powerful capability in learning representations from images/videos.

Transformers, first proposed in a Google research paper in 2017, were initially designed for natural language processing (NLP) tasks. Recently, researchers applied transformers to vision applications ...

Computer vision continues to be one of the most dynamic and impactful fields in artificial intelligence. Thanks to breakthroughs in deep learning, architecture design and data efficiency, machines are ...