0

GridMask Data Augmentation

A new structured data augmentation method called GridMask achieves state-of-the-art results in computer vision tasks by efficiently removing information from the input images, outperforming computationally expensive methods like AutoAugment.

Year
2020
Venue
arXiv 2020
Authors
5
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2001.04086v3ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

We propose a novel data augmentation method `GridMask' in this paper. It utilizes information removal to achieve state-of-the-art results in a variety of computer vision tasks. We analyze the requirement of information dropping. Then we show limitation of existing information dropping algorithms and propose our structured method, which is simple and yet very effective. It is based on the deletion of regions of the input image. Our extensive experiments show that our method outperforms the latest AutoAugment, which is way more computationally expensive due to the use of reinforcement learning to find the best policies. On the ImageNet dataset for recognition, COCO2017 object detection, and on Cityscapes dataset for semantic segmentation, our method all notably improves performance over baselines. The extensive experiments manifest the effectiveness and generality of the new method.

Authors

5