IEEE

Deformable Convolution-Guided Multiscale Feature Learning and Fusion for UAV Object Detection

Abstract: Object detection (OD) in unmanned aerial vehicle (UAV) images faces many challenges, with diverse-scale objects and small objects being particularly prominent issues. To alleviate these ...
IEEE

A Random Convolution based Adversarial Data Augmentation for Single-Source Domain Generalization

Abstract: Domain generalization, focusing on training neural networks that generalize well to unseen target domains, is a critical challenge in machine learning. While most existing approaches rely on ...
GitHub

Omni-Dimensional Dynamic Convolution

This repository is an official PyTorch implementation of "Omni-Dimensional Dynamic Convolution", ODConv for short, published by ICLR 2022 as a spotlight. ODConv is a more generalized yet elegant ...
GitHub

Content-Adaptive Non-Local Convolution for Remote Sensing Pansharpening

Abstract: Currently, machine learning-based methods for remote sensing pansharpening have progressed rapidly. However, existing pansharpening methods often do not fully exploit differentiating ...