当前位置:网站首页>【Random Erasing】《Random Erasing Data Augmentation》
【Random Erasing】《Random Erasing Data Augmentation》
2022-07-02 06:26:00 【bryant_meng】
AAAI-2020
文章目录
1 Background and Motivation
为提升 CNN 模型的泛化能力,提升 CNN 模型应对遮挡场景的鉴别能力,提出了一种数据增广方法,Random Erasing——random position with random-sized mask with random pixel
While we can manually add occluded natural images to the training set, it is costly and the levels of occlusion might be limited.
2 Related Work
Dropout / DropConect / Adaptive dropout / Stochastic Pooling / DisturbLabel / PatchShuffle
Random flipping / random cropping
3 Advantages / Contributions
提出 Random Erasing Data Augmentation,与 random cropping,random filpping 互补,not require any extra parameter learning,在分类 / 检测 / reID 任务上均有不错的效果
4 Method
1)算法流程
x e x_e xe 和 y e y_e ye 是中心点, W e W_e We 和 H e H_e He 是长宽
随机中心点,随机长宽比,随机面积,随机像素填充值
2)分类和 ReID 上的应用
简单粗暴,全图范围 random
3)目标检测上的应用
全图范围,目标范围,全图 + 目标范围
4)和 Random cropping 的区别
random cropping,可以降低背景的干扰,can base learning models on the presence of parts of the object instead of focusing on the whole object
random erasing,can be viewed as adding noise to the image
结合起来样本更加丰富
5 Experiments
5.1 Datasets and Metrics
1)数据集
分类
CIFAR-10
CIFAR-100
Fashion-MNIST检测
PASCAL VOC 2007ReID
Market-1501
DukeMTMC-reID
CUHK03
2)评价指标
分类,top-1 error rates,“mean std” based on 5 runs
检测,mAP
ReID,rank-1,mAP
5.2 Experiments
5.2.1 Image Classification
1)Classification accuracy on different datasets
p = 0.5 p = 0.5 p=0.5, s l = 0.02 s_l = 0.02 sl=0.02, s h = 0.4 s_h = 0.4 sh=0.4, and r 1 = 1 / r 2 = 0.3 r1 =1/r2= 0.3 r1=1/r2=0.3
2)The impact of hyper-parameters
fix s l s_l sl to 0.02, r 1 = 1 / r 2 r1 = 1/r2 r1=1/r2 and evaluate p p p, s h s_h sh, and r 1 r1 r1
We set p = 0.5 p = 0.5 p=0.5, s h = 0.4 s_h = 0.4 sh=0.4 and r 1 = 0.3 r1 = 0.3 r1=0.3 as the base setting. When evaluating one of the parameters, we fixed the other two parameters
都比 Baseline(没有 random erasing) 效果要更好!
3)Four types of random values for erasing
随机填充值和填充 ImageNet 的 mean 效果差不多[125, 122,114](算是明白 114 的出处了,原来那个灰白颜色是 ImageNet 的均值),优于填 0 和 255
4)Comparison with Dropout and random noise
random erasing 更胜一筹
5)Comparing with data augmentation methods
单独的话,random cropping > random flipping > random erasing
三合一 1+1+1>1,猛
6)Robustness to occlusion
手动遮挡,测试下效果 random erasing 的效果
We randomly select a region of area and fill it with random values. aspect ratio [0.3, 3.33]
秀
5.2.2 Object Detection
秀
5.2.3 Person Reidentification
秀
SOTA 配合 re-ranking,结果更进一层
6 Conclusion(own) / Future work
arXiv-2017-11-16 挂出来的论文中了 2020 AAAI,消失的时间
Deep learning: Dropout, DropConnect
12中主要的Dropout方法:如何应用于DNNs,CNNs,RNNs中的数学和可视化解释
- 《A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection》(CVPR-2017)
通过训练(对特征图进行遮挡和仿射变换)提升检测网络对遮挡、形变物体的识别精度
- 《PatchShuffle Regularization》(arXiv-2017)
边栏推荐
- win10+vs2017+denseflow编译
- iOD及Detectron2搭建过程问题记录
- PHP returns the corresponding key value according to the value in the two-dimensional array
- [torch] some ideas to solve the problem that the tensor parameters have gradients and the weight is not updated
- Typeerror in allenlp: object of type tensor is not JSON serializable error
- view的绘制机制(二)
- Calculate the difference in days, months, and years between two dates in PHP
- 自然辩证辨析题整理
- 【Ranking】Pre-trained Language Model based Ranking in Baidu Search
- Mmdetection installation problem
猜你喜欢
Error in running test pyspark in idea2020
Installation and use of image data crawling tool Image Downloader
使用 Compose 实现可见 ScrollBar
【信息检索导论】第二章 词项词典与倒排记录表
Spark SQL task performance optimization (basic)
How to efficiently develop a wechat applet
使用Matlab实现:Jacobi、Gauss-Seidel迭代
Agile development of software development pattern (scrum)
程序的执行
Three principles of architecture design
随机推荐
Using compose to realize visible scrollbar
allennlp 中的TypeError: Object of type Tensor is not JSON serializable错误
实现接口 Interface Iterable<T>
ModuleNotFoundError: No module named ‘pytest‘
SSM second hand trading website
Faster-ILOD、maskrcnn_benchmark训练自己的voc数据集及问题汇总
SSM student achievement information management system
聊天中文语料库对比(附上各资源链接)
SSM supermarket order management system
使用Matlab实现:Jacobi、Gauss-Seidel迭代
图片数据爬取工具Image-Downloader的安装和使用
Two dimensional array de duplication in PHP
[paper introduction] r-drop: regulated dropout for neural networks
一个中年程序员学习中国近代史的小结
Tencent machine test questions
使用MAME32K进行联机游戏
MMDetection模型微调
[introduction to information retrieval] Chapter II vocabulary dictionary and inverted record table
Conda 创建,复制,分享虚拟环境
Feeling after reading "agile and tidy way: return to origin"