IEEE

RefConv: Reparameterized Refocusing Convolution for Powerful ConvNets

Abstract: We propose reparameterized refocusing convolution (RefConv) as a replacement for regular convolutional layers, which is a plug-and-play module to improve the performance without any ...
GitHub

Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation

LiDAR point cloud semantic segmentation enables the robots to obtain fine-grained semantic information of the surrounding environment. Recently, many works project the point cloud onto the 2D image ...
IEEE

A Novel Tensor Causal Convolution Network Model for Highly-Accurate Representation to Spatio-Temporal Data

Abstract: Spatio-temporal data like a Dynamically Weighted Directed Network (DWDN) are ubiquitous in bigdata applications like an intelligent recommender system. They commonly illustrate the complex ...
GitHub

ESC: Emulating Self-attention with Convolution for Efficient Image Super-Resolution

In this paper, we tackle the high computational overhead of transformers for lightweight image super-resolution. (SR). Motivated by the observations of self-attention's inter-layer repetition, we ...