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 …

Fast and robust small target detection is one of the key technologies in the infrared (IR)
search and tracking systems. With the development of deep learning, there are many data …

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

Two-branch network architecture has shown its efficiency and effectiveness in real-time
semantic segmentation tasks. However, direct fusion of high-resolution details and low …

Although vision transformers (ViTs) have achieved great success in computer vision, the
heavy computational cost hampers their applications to dense prediction tasks such as …

Using light-weight architectures or reasoning on low-resolution images, recent methods
realize very fast scene parsing, even running at more than 100 FPS on a single GPU …

BiSeNet has been proved to be a popular two-stream network for real-time segmentation.
However, its principle of adding an extra path to encode spatial information is time …

Current semantic segmentation methods focus only on mining" local" context, ie,
dependencies between pixels within individual images, by context-aggregation modules …

We present an efficient high-resolution network, Lite-HRNet, for human pose estimation. We
start by simply applying the efficient shuffle block in ShuffleNet to HRNet (high-resolution …

High-resolution dense prediction enables many appealing real-world applications, such as
computational photography, autonomous driving, etc. However, the vast computational cost …