Open AccessPosted Content
GridMask Data Augmentation
Reads0
Chats0
TLDR
This paper proposes a novel data augmentation method `GridMask', which is based on the deletion of regions of the input image and outperforms the latest AutoAugment, which is way more computationally expensive due to the use of reinforcement learning to find the best policies.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.read more
Citations
More filters
Posted Content
YOLOv4: Optimal Speed and Accuracy of Object Detection
TL;DR: This work uses new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, C mBN, DropBlock regularization, and CIoU loss, and combine some of them to achieve state-of-the-art results: 43.5% AP for the MS COCO dataset at a realtime speed of ~65 FPS on Tesla V100.
Posted Content
KeepAugment: A Simple Information-Preserving Data Augmentation Approach
TL;DR: This paper empirically shows that the standard data augmentation methods may introduce distribution shift and consequently hurt the performance on unaugmented data during inference, and proposes a simple yet effective approach, dubbed KeepAugment, to increase the fidelity of augmented images.
Posted Content
PP-OCR: A Practical Ultra Lightweight OCR System
Yuning Du,Chenxia Li,Ruoyu Guo,Xiaoting Yin,Weiwei Liu,Jun Zhou,Yifan Bai,Yu Zilin,Yehua Yang,Qingqing Dang,Haoshuang Wang +10 more
TL;DR: This paper proposes a practical ultra lightweight OCR system, i.e., PP-OCR, with an overall model size of only 3.5M, and introduces a bag of strategies to either enhance the model ability or reduce the model size.
Journal ArticleDOI
Image Data Augmentation for Deep Learning: A Survey
TL;DR: A taxonomy of re-viewed methods is proposed and the strengths and limi-tations of these methods are presented and extensive experiments with various data augmentation methods on three typical computer vision tasks are conducted.
Journal ArticleDOI
A Comprehensive Survey of Image Augmentation Techniques for Deep Learning
TL;DR: A comprehensive survey of image augmentation for deep learning using a novel informative taxonomy is presented in this article , where the algorithms are classified into three categories: model-free, model-based, and optimizing policy-based.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.