GridMask Data Augmentation

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.

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fully Convolutional Networks for Semantic Segmentation
• Improved Regularization of Convolutional Neural Networks with Cutout
• Random Erasing Data Augmentation
• Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
• Shake-Shake regularization

Cited by in corpus (27)

• YOLOv4: Optimal Speed and Accuracy of Object Detection
• A Survey on Deep Semi-supervised Learning
• A Comprehensive Survey of Image Augmentation Techniques for Deep Learning
• Deepfake Detection by Human Crowds, Machines, and Machine-informed Crowds
• Automated data processing and feature engineering for deep learning and big data applications: a survey
• A New Dataset, Poisson GAN and AquaNet for Underwater Object Grabbing
• PP-OCR: A Practical Ultra Lightweight OCR System
• Cut-Thumbnail: A Novel Data Augmentation for Convolutional Neural Network
• A Large Multi-Target Dataset of Common Bengali Handwritten Graphemes
• KeepAugment: A Simple Information-Preserving Data Augmentation Approach
• AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation
• VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
• FenceMask: A Data Augmentation Approach for Pre-extracted Image Features
• T-TAME: Trainable Attention Mechanism for Explaining Convolutional Networks and Vision Transformers
• Scale-aware Automatic Augmentation for Object Detection
• When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks
• PAFNet: An Efficient Anchor-Free Object Detector Guidance
• CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing
• PriorityCut: Occlusion-guided Regularization for Warp-based Image Animation
• Mixup Without Hesitation
• DACov: A Deeper Analysis of Data Augmentation on the Computed Tomography Segmentation Problem
• SuperpixelGridCut, SuperpixelGridMean and SuperpixelGridMix Data Augmentation
• Instance Segmentation Challenge Track Technical Report, VIPriors Workshop at ICCV 2021: Task-Specific Copy-Paste Data Augmentation Method for Instance Segmentation
• Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery
• The Second Place Solution for ICCV2021 VIPriors Instance Segmentation Challenge
• Exploring Content Based Image Retrieval for Highly Imbalanced Melanoma Data using Style Transfer, Semantic Image Segmentation and Ensemble Learning
• IIE-NLP-Eyas at SemEval-2021 Task 4: Enhancing PLM for ReCAM with Special Tokens, Re-Ranking, Siamese Encoders and Back Translation