Aerial Image Dehazing Network Compression: Towards Micro-UAV’S Real-Time Online Inferencing

  • Lulu Liu
  • , Zhijun Meng*
  • , Kaipeng Wang
  • , Jiahui Zhang
  • , Zichen Wang
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Dehazing Generative Adversarial Networks (Dehazing GANs) have been widely used in the field of haze-free images. However, due to the huge computational costs and memory usage of dehazing GANs, they are difficult to be applied on the edge devices with limited resources. Although there are many efforts to solve these issues, these compressed dehazing GANs can not meet the real-time requirements on edge devices. In this way, we propose an efficient multi-granularity distillation scheme for aerial image dehazing network compression (AIDNC). We are the first one to introduce online distillation to compress dehazing GANs, where the student model is compressed by lightweight residual structure and channel pruning. In AIDNC, the student generator removes the discriminator and is optimized by the guidance information provided by gradually promoted teacher generator. Experimental results on two dehazing datasets show that AIDNC achieves 17.43 × MACs and 218.41 × parameters compression with few loss for image quality. It is proved that AIDNC is an efficient framework for the aerial image real-time dehazing on edge devices, like micro-UAVs.

Original languageEnglish
Title of host publicationProceedings of International Conference on Image, Vision and Intelligent Systems, ICIVIS 2022
EditorsPeng You, Heng Li, Zhenxiang Chen
PublisherSpringer Science and Business Media Deutschland GmbH
Pages442-453
Number of pages12
ISBN (Print)9789819909223
DOIs
StatePublished - 2023
Event2nd International Conference on Image, Vision and Intelligent Systems, ICIVIS 2022 - Jinan, China
Duration: 15 Aug 202217 Aug 2022

Publication series

NameLecture Notes in Electrical Engineering
Volume1019 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference2nd International Conference on Image, Vision and Intelligent Systems, ICIVIS 2022
Country/TerritoryChina
CityJinan
Period15/08/2217/08/22

Keywords

  • Depthwise separable convolution
  • Generative adversarial network compression
  • Image dehazing
  • Knowledge distillation

Fingerprint

Dive into the research topics of 'Aerial Image Dehazing Network Compression: Towards Micro-UAV’S Real-Time Online Inferencing'. Together they form a unique fingerprint.

Cite this