Zehan Chen

2 accepted papers

2022

MAKD: MULTIPLE Auxiliary Knowledge Distillation

ICASSP 2022accepted

Knowledge distillation aims to learn a small student model by leveraging knowledge from a larger teacher model. The gap between these heterogeneous models hinder their knowledge transfer and it would be more challenging when the teacher model is from another task. Previous methods view the teacher m…

Cited by 0 Source ↗Scholar ↗

2018

Inverse Atmoshperic Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing

Zehan Chen, Yi Wang, Yuexian Zou

ICASSP 2018accepted

Single image dehazing is an ill-posed problem. Most existing works use the atmospheric scattering model (ASM) [1] and some natural priors to dehazing. Recently, DehazeNet [2] was developed using deep learning approach achieves the state-of-the-art results on many test hazy images, which motivates us…

Cited by 0 Source ↗Scholar ↗