当前位置:网站首页>[CV-Learning] Semantic Segmentation
[CV-Learning] Semantic Segmentation
2022-08-04 06:06:00 【Xiao Liang has to work hard】
Semantic segmentation
Definition: Assign a class label to each pixel of an image, regardless of instance, only consider pixel class.
Old ideas (sliding window)
Ideas: Take a certain pixel as the center, select an area, and classify the area.
Problem: The efficiency is too low, and the overlapping area features are calculated repeatedly.
New idea (full convolution)
Idea: Perform pooling during Convolutions to keep the image size and depth unchanged, and then obtain Scores with a depth of C, where each depth represents a category, and each pixel can be judged by category.Finally, by judging the sum of the cross-entropy loss of each pixel, the total loss is controlled by feedback, and the lower the better.
Problem: The original resolution of the image is maintained during the Convolutions process, which requires a huge amount of video memory.Therefore, the Convolutions process can be optimized to improve performance.
Performance improvements
Ideas: In the process of Convolutions, first down-sampling is performed to extract high-level semantic features, and then the original learning is returned through up-sampling to establish a high-level semantic-to-classmark mapping.
Downsampling
pooling, strided convolution
Upsample t
unpooling or strided transpose convolution
Hard-coded upsampling
Learnable Upsampling (Transpose convolution)
Downsampling
Upsampling
One-dimensional upsampling example
Filter is a filter kernel, which is a matrix that can be learned.
Convolution and matrix multiplication (one-dimensional)
The following legends are down-sampling first, and then up-sampling restoration.
Example 1: Step 1
Example2: Step size is 2
UNET
Upsampling is obtained based on the high-level semantics obtained by downsampling, but sometimes the high-level semantics do not work well, and low-level semantics need to be used.
In response to this problem, UNET is proposed, which integrates the low-level semantics in the downsampling process into the upsampling process, resulting in better results.
Integration ideas:
1. Copy the red feature channel on the left and combine it with the upsampled feature channel.
2. After the red feature channel on the left is processed by convolution, it is combined with the up-sampled feature channel.
边栏推荐
- Kubernetes基本入门-集群资源(二)
- Redis持久化方式RDB和AOF详解
- (九)哈希表
- fill_between in Matplotlib; np.argsort() function
- 剑指 Offer 2022/7/11
- 【CV-Learning】图像分类
- k3s-轻量级Kubernetes
- 判断字符串是否有子字符串重复出现
- [Deep Learning 21 Days Learning Challenge] 2. Complex sample classification and recognition - convolutional neural network (CNN) clothing image classification
- 【CV-Learning】线性分类器(SVM基础)
猜你喜欢
TensorFlow2 study notes: 5. Common activation functions
Kubernetes基本入门-集群资源(二)
Jupyter Notebook安装库;ModuleNotFoundError: No module named ‘plotly‘解决方案。
智能合约安全——delegatecall (2)
完美解决keyby造成的数据倾斜导致吞吐量降低的问题
Thoroughly understand box plot analysis
【go语言入门笔记】12、指针
Th in thymeleaf: href use notes
【CV-Learning】语义分割
【深度学习21天学习挑战赛】备忘篇:我们的神经网模型到底长啥样?——model.summary()详解
随机推荐
剑指 Offer 2022/7/8
逻辑回归---简介、API简介、案例:癌症分类预测、分类评估法以及ROC曲线和AUC指标
TensorFlow2 study notes: 7. Optimizer
读研碎碎念
ReentrantLock(公平锁、非公平锁)可重入锁原理
postgres 递归查询
oracle临时表与pg临时表的区别
flink-sql所有语法详解
剑指 Offer 20226/30
SQl练习 2022/6/29
【深度学习21天学习挑战赛】3、使用自制数据集——卷积神经网络(CNN)天气识别
SQL的性能分析、优化
网络大作业心得笔记
Kubernetes基本入门-概念介绍(一)
sklearn中的学习曲线learning_curve函数
【CV-Learning】卷积神经网络预备知识
Kubernetes基本入门-名称空间资源(三)
TensorFlow:tf.ConfigProto()与Session
Introduction of linear regression 01 - API use cases
TensorFlow2学习笔记:6、过拟合和欠拟合,及其缓解方案