MeshCut data augmentation for deep learning in computer vision

PLoS One. 2020 Dec 23;15(12):e0243613. doi: 10.1371/journal.pone.0243613. eCollection 2020.

Abstract

To solve overfitting in machine learning, we propose a novel data augmentation method called MeshCut, which uses a mesh-like mask to segment the whole image to achieve more partial diversified information. In our experiments, this strategy outperformed the existing augmentation strategies and achieved state-of-the-art results in a variety of computer vision tasks. MeshCut is also an easy-to-implement strategy that can efficiently improve the performance of the existing convolutional neural network models by a good margin without careful hand-tuning. The performance of such a strategy can be further improved by incorporating it into other augmentation strategies, which can make MeshCut a promising baseline strategy for future data augmentation algorithms.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms
  • Data Accuracy
  • Deep Learning*
  • Image Processing, Computer-Assisted / methods*

Grants and funding

The project of Sichuan Province Science and Technology Support Program under Grant 2019YFG0373; The Major Special Projects of Sichuan Province under Grant 2020ZDZX0024; Department of Science and Technology of Sichuan Province, 2019YFG0397.