Breaking Through the Haze: An Advanced Non-Homogeneous Dehazing Method based on Fast Fourier Convolution and ConvNeXt

1 code implementation • 8 May 2023 • Han Zhou, Wei Dong, Yangyi Liu, Jun Chen

To tackle these two challenges, we propose a novel two branch network that leverages 2D discrete wavelete transform (DWT), fast Fourier convolution (FFC) residual block and a pretrained ConvNeXt model.

A Data-Centric Solution to NonHomogeneous Dehazing via Vision Transformer

1 code implementation • 16 Apr 2023 • Yangyi Liu, Huan Liu, Liangyan Li, Zijun Wu, Jun Chen

Although it is possible to augment the NH-HAZE23 dataset by leveraging other non-homogeneous dehazing datasets, we observe that it is necessary to design a proper data-preprocessing approach that reduces the distribution gaps between the target dataset and the augmented one.

Image Dehazing

M22: A Communication-Efficient Algorithm for Federated Learning Inspired by Rate-Distortion

no code implementations • 23 Jan 2023 • Yangyi Liu, Stefano Rini, Sadaf Salehkalaibar, Jun Chen

This paper proposes ``\emph{${\bf M}$-magnitude weighted $L_{\bf 2}$ distortion + $\bf 2$ degrees of freedom''} (M22) algorithm, a rate-distortion inspired approach to gradient compression for federated training of deep neural networks (DNNs).

Federated Learning