Humans can naturally and effectively find salient regions in complex scenes. Motivated by
this observation, attention mechanisms were introduced into computer vision with the aim of …

The goal of semantic segmentation is to segment the input image according to semantic
information and predict the semantic category of each pixel from a given label set. With the …

We present SegNeXt, a simple convolutional network architecture for semantic
segmentation. Recent transformer-based models have dominated the field of se-mantic …

We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by
recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few …

The Transformer network was originally proposed for natural language processing. Due to
its powerful representation ability for long-range dependency, it has been extended for …

Visual segmentation seeks to partition images, video frames, or point clouds into multiple
segments or groups. This technique has numerous real-world applications, such as …

Global context information is essential for the semantic segmentation of remote sensing (RS)
images. However, most existing methods rely on a convolutional neural network (CNN) …

Recently few-shot segmentation (FSS) has been extensively developed. Most previous
works strive to achieve generalization through the meta-learning framework derived from …

We present SegFormer, a simple, efficient yet powerful semantic segmentation framework
which unifies Transformers with lightweight multilayer perceptron (MLP) decoders …

Very recently, a variety of vision transformer architectures for dense prediction tasks have
been proposed and they show that the design of spatial attention is critical to their success in …