Skip to main navigation Skip to search Skip to main content

A Lightweight Tire Tread Image Classification Network

  • Fenglei Zhang
  • , Da Li
  • , Shenghua Li
  • , Weili Guan
  • , Meng Liu
  • Shandong Jianzhu University
  • Monash University

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

Abstract

VCIP 2022 'Tire pattern image classification based on lightweight network challenge' aims to design lightweight networks that correctly classify tire surface tread patterns and indentation images using less overhead. To this end, we present a novel lightweight tire tread classification network. Concretely, we adopt the ShuffleNet-V2-x0.5 network as our backbone. To reduce the computation complexity, we introduce the Space-To-Depth and Anti-Alias Downsampling modules to pre-process the input image. Moreover, to enhance the classification ability of our model, we adopt the knowledge distillation strategy by considering Vision Transformer as the teacher network. To ensure the robustness of our model, we pre-train it on ImageNet and fine-tune the training set of the challenge. Experiments on the challenge dataset demonstrate that our model achieves supe-rior performance, with 99.00% classification accuracy, 25.51M FLOPs, and 0.20M parameters.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Visual Communications and Image Processing, VCIP 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665475921
DOIs
StatePublished - 2022
Externally publishedYes
Event2022 IEEE International Conference on Visual Communications and Image Processing, VCIP 2022 - Suzhou, China
Duration: 13 Dec 202216 Dec 2022

Publication series

Name2022 IEEE International Conference on Visual Communications and Image Processing, VCIP 2022

Conference

Conference2022 IEEE International Conference on Visual Communications and Image Processing, VCIP 2022
Country/TerritoryChina
CitySuzhou
Period13/12/2216/12/22

Keywords

  • knowledge distillation
  • lightweight image classification
  • tire tread image classification

Fingerprint

Dive into the research topics of 'A Lightweight Tire Tread Image Classification Network'. Together they form a unique fingerprint.

Cite this