-
X-volution: On the Uniļ¬cation of Convolution and Self-attention
Convolution and self-attention are acting as two fundamental building blocks in deep neural networks, where the former extracts local image features in a linear way while the... -
Im2win: An Efficient Convolution Paradigm on GPU
Convolutional neural network (CNN) is an important network model widely used in computer vision, image processing, and scientific computing. CNN consists of an input layer, an... -
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmen...
LiDAR point-cloud segmentation is an important problem for many applications. For large-scale point cloud segmentation, the de facto method is to project a 3D point cloud to get...
