GridMask Data Augmentation

By Pengguang Chen, Shu Liu, Hengshuang Zhao, Jiaya Jia. arXiv.org, 2020

380 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/41574aaa671aa55ad8ac15eb7b21c0b17bfca49a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

A Comprehensive Survey of Image Augmentation Techniques for Deep Learning (2022, methodology): “GridMask [26] 2020 Apply multiscale grid masks to an image to mimic occlusions.”
PP-OCR: A Practical Ultra Lightweight OCR System (2020, background): “2020), HideAndSeek (Singh and Lee 2017), GridMask (Chen 2020), Mixup (Zhang et al.”
A Survey on Deep Semi-Supervised Learning (2021, background): “Another promising approach is data augmentation (adding noise or random perturbations, CutOut [243], RandomErasing [258], HideAndSeek [259] and GridMask [260]), especially advanced data augmentation, such as AutoAugment [185], RandAugment [228], CTAugment [72], and Mixup [241] which also can be cons”
YOLOv4: Optimal Speed and Accuracy of Object Detection (2020, background): “As for hide-and-seek [69] and grid mask [6], they randomly or evenly select multiple rectangle regions in an image and replace them to all zeros.”
Image Data Augmentation for Deep Learning: A Survey (2022, methodology): “However, it does not provide an evaluation on the effectiveness of data augmentation for various actual tasks and lacks some newly proposed methods, such as, Cut-Mix [ Yun et al. , 2019 ] , AugMix [ Hendrycks et al. , 2019 ] , GridMask [ Chen et al. , 2020 ] , etc.”