语义分割--Loss Max-Pooling for Semantic Image Segmentation
Loss Max-Pooling for Semantic Image Segmentation
CVPR2017
https://arxiv.org/abs/1704.02966
本文采用偏数学语言的角度来描述语义分割样本类别分布不均匀问题,提出一个方法 Pixel-Loss Max-Pooling
本文主要解决什么问题了? 针对语义分割训练样本类别分布不均匀问题
handle imbalanced (or skewed) class distributions, as often encountered in semantic segmentation datasets, within deep neural network training so far.
With imbalanced, we refer to datasets having dominant portions of their data assigned to (few) majority classes while the rest belongs to minority classes, forming comparably under-represented categories.
As (mostly undesired) consequence, it can be observed that classifiers trained without correction mechanisms tend to be biased towards the majority classes during inference
这里所说的不均匀,就是我们的训练数据库有少数类别的样本很多( (few) majority classes),剩下的类别的样本都比较少。 如果在训练的时候没有修正这个不均匀,那么学习到的分类器就会偏向于 那些少数样本很多的类。
解决这个问题目前有几个思路:
1)就是在建立数据库的时候就注意到样本的均匀分布问题,例如 ImageNet, Caltech101/256 or CIFAR10/100
2)通过对样本少的类别 over-sampling 或 对样本多的类别 under-sampling
over-sampling of minority classes or under-sampling from the majority classes when compiling the actual training data
3)通过引入样本类别分布的权值来改变算法行为
cost-sensitive learning changes the algorithmic behavior by introducing class-specific weights, often derived from the original data statistics
首先使用一个数学公式描述语义分割问题
其中 L 是 loss function penalizing wrong image labelings, R 是一个 regularizer
The loss function L commonly decomposes into a sum of pixel-specific losses as follows
The loss function defined in (2) weights uniformly the contribution of each pixel within the image.
上面定义的损失函数默认图像中每个像素的权重是均匀分布的
The effect of this choice is a bias of the learner towards elements that are dominant within the image (e.g. sky, building, road) to the detriment of elements occupying smaller portions of the image
这使得学习器偏向于图像中占比大的区域,相对忽略占比小的区域
In order to alleviate this issue, we propose to adaptively reweigh the contribution of each pixel
based on the actual loss we observe
Our goal is to shift the focus on image parts where the loss is higher, while re-taining a theoretical link to the loss in (2). The solution we propose is an upper bound to L, which is constructed by relaxing the pixel weighting scheme
这里主要是给每个像素的权值引入一个上限 L,就是占比大的像素权值有一个上限,这样防止学习到的分类器有偏向性。
如果从样本类别分布不均匀的角度来说,我们对每个样本类型乘以一个权重系数,达到归一化的目的。
Cityscapes validation set
Evolution of semantic segmentation images during training
Cityscapes Pascal VOC 2012 validation
ResNet based results on Pascal VOC 2012 segmentation validation data
语义分割--Loss Max-Pooling for Semantic Image Segmentation相关推荐
- 语义分割--Deep Dual Learning for Semantic Image Segmentation
Deep Dual Learning for Semantic Image Segmentation ICCV2017 针对语义分割问题,本文提出了一个 dual image segmentation ...
- 语义分割--Attention to Scale: Scale-aware Semantic Image Segmentation
Attention to Scale: Scale-aware Semantic Image Segmentation CVPR2016 http://liangchiehchen.com/proje ...
- 语义分割 DeepLabv3--Rethinking Atrous Convolution for Semantic Image Segmentation
Rethinking Atrous Convolution for Semantic Image Segmentation https://arxiv.org/abs/1706.05587v1 代码还 ...
- 语义分割--Global Deconvolutional Networks for Semantic Segmentation
语义分割 Global Deconvolutional Networks for Semantic Segmentation BMVC 2016 https://github.com/DrSleep/ ...
- 语义分割--Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes CVPR2017 Theano/Lasagne ...
- 语义分割CVPR2020-Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision
Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision:基于自监督的非监督域内自 ...
- 语义分割--Mix-and-Match Tuning for Self-Supervised Semantic Segmentation
Mix-and-Match Tuning for Self-Supervised Semantic Segmentation AAAI Conference on Artificial Intelli ...
- 语义分割--DeconvNet--Learning Deconvolution Network for Semantic Segmentation
Learning Deconvolution Network for Semantic Segmentation ICCV2015 http://cvlab.postech.ac.kr/researc ...
- [轻量化语义分割] Rethinking BiSeNet For Real-time Semantic Segmentation(CVPR2021)
paper:https://openaccess.thecvf.com/content/CVPR2021/papers/Fan_Rethinking_BiSeNet_for_Real-Time_Sem ...
最新文章
- cx_oracle写日志信息_日志系统的设计
- matlab 2014a 升级,MATLAB R2014a从入门到精通(升级版) pdf扫描版[42MB]
- python语言有什么用-python语言为什么好呢?它有什么特点?
- 什么函数不能声明为虚函数
- c# 访问hbase_大数据技术 windows下C#通过Thrift操作HBase
- div自动滚动_实现图片自动和手动切换的编程技巧
- delphi libeay32 各版本_Zbrush各版本合集
- C++学习笔记:(七)C语言实现面向对象编程
- spring4.x aop拦截spring mvc controller
- Python机器学习实践:决策树判别汽车金融违约用户
- C++之char*,const char*和string的相互转换
- 嵌套饼图_旭日图的效率,高到饼图都羡慕
- GridView 中 Bind和Eval的区别详解
- 使用Seq2Seq+attention实现简单的Chatbot
- java aix_如何在AIX下安装JAVA
- Ant的使用 - 简单介绍
- Git报错:Pulling without specifying how to reconcile divergent branches is discouraged. You can squelch
- coursera和udacity_从Udacity和Coursera进行深度学习
- 计算机word打开,电脑word打不开怎么办
- Your application has presented a UIAlertController of style UIAlertControllerStyleActionSheet.