当前位置:网站首页>[point cloud series] unsupervised multi task feature learning on point clouds
[point cloud series] unsupervised multi task feature learning on point clouds
2022-04-23 13:18:00 【^_^ Min Fei】
1. Summary
subject :Unsupervised Multi-Task Feature Learning on Point Clouds
The paper :https://openaccess.thecvf.com/content_ICCV_2019/papers/Hassani_Unsupervised_Multi-Task_Feature_Learning_on_Point_Clouds_ICCV_2019_paper.pdf
2. motivation
Traditional manual design features mainly capture local or global statistical attributes , Unable to represent semantic properties .
Is there a common feature for tasks that require semantic features ?
So this article This paper puts forward a method which can be used for unsupervised multitasking Feature expression of the model , Encoder based on multiscale graph . End to end training .
3. Algorithm
For three unsupervised learning tasks :
- clustering
- restructure
- Self supervised classification
The overall framework :
decoder : Multi scale ( Graph convolution + Convolution + Pooling )+ Perturbed Gaussian noise
Essentially applicable to multitasking , It's also because we used the loss of these tasks to train together , Naturally, with this function .
Definition of volume of drawing : It's actually the residual between two points ;
Algorithm description :
Training set : S = { s 1 , s 2 , . . . , s N } S=\{s_1, s_2, ..., s_N\} S={
s1,s2,...,sN},N A little bit .
One point : s i = { p 1 i , p 2 i , . . , p M 1 } s_i =\{ p^i_1, p^i_2, .., p^1_M\} si={
p1i,p2i,..,pM1}, M A disordered point , p j i = ( x j i , y j i , z j i ) p^i_j=(x^i_j, y^i_j, z^i_j) pji=(xji,yji,zji) Include coordinates only
Encoder : E θ : S ( R M × d i n ) → Z ( R d z ) E_{\theta}: S (\mathbb{R}^{M\times d_{in}})\rightarrow Z (\mathbb{R}^{d_z}) Eθ:S(RM×din)→Z(Rdz), d z d_z dz Far greater than d i n d_in din
In order to learn more tasks than supervision θ \theta θ, Design the following three parameter functions :
Clustering function T c : Z → y \Tau_c:Z \rightarrow y Tc:Z→y, Classify hidden codes into K K K Of the three categories , among y = [ y 1 , y 2 , . . . , y n ] y=[y_1, y_2, ...,y_n] y=[y1,y2,...,yn], y i ∈ { 0 , 1 } K y_i\in\{0,1\}^K yi∈{
0,1}K, And y n T 1 k = 1 y^T_n \mathbf{1}_k=1 ynT1k=1.
Classification function f ψ : Z → y ^ f_\psi: Z \rightarrow \hat{y} fψ:Z→y^, Category prediction after clustering , In other words , The classification function maps implicit variables to K A prediction class y ^ = [ y 1 ^ , y 2 ^ , . . . , y n ^ ] \hat{y}=[\hat{y_1}, \hat{y_2}, ...,\hat{y_n}] y^=[y1^,y2^,...,yn^], And y i ^ ∈ { 0 , 1 } K \hat{y_i}\in\{0,1\}^K yi^∈{
0,1}K. The function uses the pseudo tag generated by the clustering function as the agent training data .
Decoder function : g ϕ : Z ( R d z ) → S ^ ( R M × d i n ) g_\phi: Z(\mathbb{R}^{d_z}) \rightarrow \hat{S} (\mathbb{R}^{M\times d_{in}}) gϕ:Z(Rdz)→S^(RM×din), Reconstruct the implicit variable back to the point cloud . If only clustering loss is used, the features will be clustered into a single class , The function is designed to prevent the final aggregation into a single class .
Loss of training :
-
Clustering loss : In essence, it is learning the clustering center matrix : C ∈ R d z × K C\in \mathbb{R}^{d_z \times K} C∈Rdz×K, z n = E θ ( s n ) z_n=E_\theta(sn) zn=Eθ(sn), y n T 1 k = 1 y^T_n\mathbf{1}_k=1 ynT1k=1. among , initialization The random clustering matrix is the center , yes epoch The updated .
-
Classified loss : Cross entropy measures , y n = T c ( z n ) y_n=\Tau_c(z_n) yn=Tc(zn), y ^ n = f ψ ( z n ) \hat{y}_n=f_\psi(z_n) y^n=fψ(zn).
-
Refactoring loss :CD distance . s ^ n = g ϕ ( z n ) \hat{s}_n=g_\phi (z_n) s^n=gϕ(zn) Is the reconstructed point set , s n s_n sn yes GT. N N N: Number of training sets ; M M M: The number of points in each point set .
The ultimate loss : above 3 Weighted summation of losses
The specific description process is shown in the following figure 1 Shown :
4. experiment
Model convergence :88 Classes , actual 55 Category .
The Clustering Visualization diagram is as follows :
On classified tasks , Comparison of unsupervised and supervised methods : It works well in unsupervised methods ;
The effect of semi supervised segmentation task : 5% The effect of the training set is still very good ;
Split task effect :
Encoder The role of , Test on classification tasks : In fact, it seems to be saying here , complex Encoder The improvement after refactoring is not particularly great , The improvement of multi class tasks is very big .
Ablation Experiment : Refactoring is the key , Plus the effect of classification > The effect of clustering , Because clustering here is actually for further classification , Realize the so-called unsupervised .
5. Conclusion and thinking
Failure case list :
- apply K-Means To initialize the cluster center , But there is no improvement in the random clustering center method ;
- stay decoder And classification model soft Shared parameter mechanism , It is found that the effect is reduced , So separate the two ;
- Try to iterate over more layers , Recalculate the nearest neighbor at each layer , It is found that this is disadvantageous to classification and segmentation ;
版权声明
本文为[^_^ Min Fei]所创,转载请带上原文链接,感谢
https://yzsam.com/2022/04/202204230611136498.html
边栏推荐
- uniapp image 引入本地图片不显示
- The filter() traverses the array, which is extremely friendly
- Imx6ull QEMU bare metal tutorial 2: usdhc SD card
- web三大组件之Filter、Listener
- [quick platoon] 215 The kth largest element in the array
- FFmpeg常用命令
- ESP32 VHCI架构传统蓝牙设置scan mode,让设备能被搜索到
- PyTorch 21. NN in pytorch Embedding module
- Armv8m (cortex M33) MPU actual combat
- 【官宣】长沙软件人才实训基地成立!
猜你喜欢
[untitled] PID control TT encoder motor
X509 parsing
Summary of request and response and their ServletContext
How to build a line of code with M4 qprotex
Kernel error: no rule to make target 'Debian / canonical certs pem‘, needed by ‘certs/x509_ certificate_ list‘
Nodejs + websocket cycle small case
100 GIS practical application cases (51) - a method for calculating the hourly spatial average of NC files according to the specified range in ArcGIS
FatFs FAT32 learning notes
LeetCode_DFS_中等_695.岛屿的最大面积
CSDN高校俱乐部“名师高校行”——湖南师范大学站
随机推荐
数据仓库—什么是OLAP
Solve the problem of Oracle Chinese garbled code
[quick platoon] 215 The kth largest element in the array
在 pytorch 中加载和使用图像分类数据集 Fashion-MNIST
These vscode extensions are my favorite
100000 college students have become ape powder. What are you waiting for?
十万大学生都已成为猿粉,你还在等什么?
ESP32 VHCI架构传统蓝牙设置scan mode,让设备能被搜索到
MySQL -- 16. Data structure of index
Data warehouse - what is OLAP
Super 40W bonus pool waiting for you to fight! The second "Changsha bank Cup" Tencent yunqi innovation competition is hot!
Lpddr4 notes
XML
Async void caused the program to crash
[untitled] PID control TT encoder motor
【官宣】长沙软件人才实训基地成立!
LeetCode_ DFS_ Medium_ 695. Maximum area of the island
Melt reshape decast long data short data length conversion data cleaning row column conversion
Translation of attention in natural language processing
Vscode tips