Following unprecedented success on the natural language tasks, Transformers have been
successfully applied to several computer vision problems, achieving state-of-the-art results …

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 …

To design fast neural networks, many works have been focusing on reducing the number of
floating-point operations (FLOPs). We observe that such reduction in FLOPs, however, does …

Real-time object detection is one of the most important research topics in computer vision.
As new approaches regarding architecture optimization and training optimization are …

Structural pruning enables model acceleration by removing structurally-grouped parameters
from neural networks. However, the parameter-grouping patterns vary widely across …

PointNet++ is one of the most influential neural architectures for point cloud understanding.
Although the accuracy of PointNet++ has been largely surpassed by recent networks such …

Vision transformers have shown great success due to their high model capabilities.
However, their remarkable performance is accompanied by heavy computation costs, which …

Multi-modality (MM) image fusion aims to render fused images that maintain the merits of
different modalities, eg, functional highlight and detailed textures. To tackle the challenge in …

Light-weight convolutional neural networks (CNNs) are specially designed for applications
on mobile devices with faster inference speed. The convolutional operation can only capture …

The quadratic computation complexity of self-attention has been a persistent challenge
when applying Transformer models to vision tasks. Linear attention, on the other hand, offers …