Fine-grained apparel image recognition based on deep learning

Jia He, Xi Jia, Junli Li, Shiqi Yu, Linlin Shen

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

1 Citation (Scopus)


There are many styles and details of apparel, including coat length, collar design, sleeve length and other detail properties. The e-commerce platform that manages apparel products needs to quickly and effectively identify the attribute categories of apparel for quick retrieval. Apparel image data contains many detailed features that can be easily deformed and occluded. Traditional image recognition technology has been unable to meet the requirements of its classification accuracy. The neural network based on deep learning can classify the fine-grained attributes of complex objects well after training. In this work, we use the apparel image data to train convolutional neural network for the classification of fine-grained attributes. To improve the classification accuracy, we also integrate the results of different models. The experiments show that the results of multi-model fusion are better than those of single model.

Original languageEnglish
Title of host publicationArtificial Intelligence on Fashion and Textiles - Proceedings of the Artificial Intelligence on Fashion and Textiles AIFT Conference 2018
EditorsWai Keung Wong
PublisherSpringer Verlag
Number of pages8
ISBN (Print)9783319996943
Publication statusPublished - 2019
Externally publishedYes
EventArtificial Intelligence on Fashion and Textiles Conference, AIFT 2018 - Hong Kong, China
Duration: 27 Jun 201829 Jun 2018

Publication series

NameAdvances in Intelligent Systems and Computing
ISSN (Print)2194-5357


ConferenceArtificial Intelligence on Fashion and Textiles Conference, AIFT 2018
CityHong Kong


  • CNN
  • Deep learning
  • Fine-grained image recognition

ASJC Scopus subject areas

  • Control and Systems Engineering
  • General Computer Science


Dive into the research topics of 'Fine-grained apparel image recognition based on deep learning'. Together they form a unique fingerprint.

Cite this