Validation Feedback based Image Transfer Network for Data Augmentation

Weili Chen, Seiichiro Kamata, Zitang Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Modern image classifiers are often suffering over-fitting problems because of the insufficient number of images in the dataset. Data augmentation is a strategy to increase the number of training samples. However, recent data augmentation methods are designed manually and cannot generate real-like images. Some neural network-based image generation methods such as GAN and VAE can also be used for data augmentation, but they are usually applied to unbalanced datasets. Since the generated images cannot be guaranteed to be from the same label, using them to extend a balanced dataset may lead to decreasing the accuracy of the classifier. In this paper, we propose an image transfer network to produce images that automatically adapt to a specific dataset and classifier. The image transfer network will search for the output images which can maximize the validation accuracy and help the classifier to overcome the over-fitting problems. Through the experiments, our method achieves high accuracy on CIFAR-10 and CIFAR-100 datasets. Moreover, since it could combine with other data augmentation methods, we show that using our method can push the state-of-the-art results furthermore.

Original languageEnglish
Title of host publicationProceedings of 2020 2nd International Conference on Video, Signal and Image Processing, VSIP 2020
PublisherAssociation for Computing Machinery
Pages23-29
Number of pages7
ISBN (Electronic)9781450388931
DOIs
Publication statusPublished - 2020 Apr 12
Event2nd International Conference on Video, Signal and Image Processing, VSIP 2020 - Virtual, Online, Indonesia
Duration: 2020 Dec 42020 Dec 6

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2nd International Conference on Video, Signal and Image Processing, VSIP 2020
CountryIndonesia
CityVirtual, Online
Period20/12/420/12/6

Keywords

  • Data augmentation
  • Machine learning
  • Neural Network

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint Dive into the research topics of 'Validation Feedback based Image Transfer Network for Data Augmentation'. Together they form a unique fingerprint.

Cite this