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 ...
IEEE

Revisiting Deformable Convolution on Graphs: Large-range Modeling and Robustness

Abstract: Graph Convolution Networks (GCNs) have achieved remarkable success in representation of structured graph data. As we know that traditional GCNs are generally defined on the fixed first-order ...
GitHub

Extension Points Examples (Beta)

You can extend various functionalities of the MATLAB® desktop using Extension Points. For example, you can add custom items to the Quick Access Toolbar or change the icon or label for a file type in ...
IEEE

Graph-Structured Convolution-Guided Continuous Context Threshold-Aware Networks for Hyperspectral Image Classification

Abstract: Although convolutional neural networks (CNNs) have shown superior performance to traditional machine learning algorithms for hyperspectral image (HSI) classification tasks, the ability of ...