笔记:基于点云的语义分割的小样本学习
笔记:Few-shot learning for tackling open-set generalization:
基于点云的语义分割的应用:场景理解,给点云中每一个点赋予特点的语义标签。(如自动驾驶)
小样本学习的意义:解决太过于依赖大量标定数据,减少成本;可以提高泛化能力,识别未曾见过的目标。
paper1:Few-shot 3D Point Cloud Semantic Segmentation
提出问题:
- rely on large amounts of labeled training data, so they are time-consuming and expensive to collect.
- follow the closed set assumption.(训练集和测试集取自同一label space) ,泛化能力差。
解决:
multi-prototype transductive inference method.
- transductive inference: 转导推理;是一种通过观察特点的样本,进而预测特定的测试样本的方法,是一种从特殊到特殊的推理,适合于小样本推理。不同于归纳推理,先从训练样本中学习规则,再用规则判断测试样本。
architecture:
embedding network:
- three properties:1.local geometric features; 2.global geometric features; 3. adapt to different few-shot tasks.
- DGGNN: the backbone of feature extractor.(local)
- SAN(self-attention network): generate semantic feature.(global)
- MLP: adapt to different few-shot tasks.
multi-prototype generation:
- It samples a subset of n seed points from a set of support points in one class using the farthest point sampling based on the embedding space.(对support set的每一类样本点farthest points sample,抽取n个seed point)
- The farthest points represent different perspectives of one class. (farthest points sample保证足够的感受野)
transductive inference:
use transductive label propagation to construct a graph on the labeled multi-prototypes and the unlabeled query points.(用k-NN建立相关类的图)
label propagation
cross-entropy loss function(交叉熵损失函数):
- compute the cross-entropy loss with ground truth labels.
paper2:What Makes for Effective Few-shot Point Cloud Classification?
提出问题:
- they require extensive data collection and retraining when dealing with novel classes never seen before.
- It is hard to study from existing 2D methods when migrating to the 3D domain.
- point clouds are more complex and have unorder structure in European space.
3D point cloud classification
- projection-based: It first converts the irregular points into a representation like voxel, pillar, and then apply typical 2D or 3D CNN to extract features.
- point-based: It can learns point-wise features with multilayer perceptron(MLP) and aggregates global feature with a symmetric function implemented by a max-pooling layer.
2D few-shot learning
- Metric-based: It focus on learning an embedding space where similar samples pairs are closer, or designing a metric function to compare the feature similarity of samples.
- Optimization-based: It regards meta-learning as an optimization process.
State-of-the-art 2D FSL on Point Cloud
- compare the metric-based methods and optimization-based methods, and concludes that metric-based methods outperform the optimization-based methods in point cloud scenario.
Influence of Backbone Architecture on FSL
- select three types of current state-of-the-art 3D point-based networks including Pointwise-based, Convolution-based, Graph-based(DGCNN). One can conclude that the graph-based network DGCNN achieves higher classification accuracy than other networks on these two datasets.
Cross Instance Adaption (CIA) module
CIA can be inserted into existing backbones and learning frameworks to learn more discriminative representations for the support set and query set.
Embedding module把support-set和query-set作为输入分别进行特征提取得到他们的prototype,然后再通过CIA模块更新support-set和query-set,然后在特征空间计算每个class prototype和query examples的欧氏距离,最后便可得到损失函数并进行优化。
Self-Channel Interaction Module: address the issues of subtle inter-class differences.
- 先从embedding space分别由两个线性系数φ和γ得到q向量和k向量,然后通过CIM的双线性变换得到一个channel-wise relation score map - R, 然后进行softmax操作得到权重矩阵R’,最后得到更新的向量v是有R’与开始的特征向量加权和得到,vi越大说明特供信息越大,有利于区分class之间的细小差别。
Cross-Instance Fusion Module: address high intra-class variances issues
- 首先将support feature和query feature 连结起来得到Z,然后用两个卷积层来解码连结后的特征得到W,将W进行softmax操作得到权值矩阵后与Z点乘来更新support feature和query feature。
本文还提供了两个适用于3D FSL的数据集:ModelNet40-FS,ShapeNet70-FS
笔记:基于点云的语义分割的小样本学习相关推荐
- 笔记:基于DCNN的图像语义分割综述
写在前面:一篇魏云超博士的综述论文,完整题目为<基于DCNN的图像语义分割综述>,在这里选择性摘抄和理解,以加深自己印象,同时达到对近年来图像语义分割历史学习和了解的目的,博古才能通今!感 ...
- 使用Pytorch搭建U-Net网络并基于DRIVE数据集训练(语义分割)学习笔记
使用Pytorch搭建U-Net网络并基于DRIVE数据集训练(语义分割)学习笔记 https://www.bilibili.com/video/BV1rq4y1w7xM?spm_id_from=33 ...
- 大场景三维点云的语义分割综述
点击上方"3D视觉工坊",选择"星标" 干货第一时间送达 来源:点云PCL 一.点云语义分割 输入原始点云(x,y,z,intensity),得到每个三维点的语 ...
- 【深度学习】SETR:基于视觉 Transformer 的语义分割模型
Visual Transformer Author:louwill Machine Learning Lab 自从Transformer在视觉领域大火之后,一系列下游视觉任务应用研究也随之多了起来.基 ...
- 基于MindSpore复现Deeplabv3—语义分割
基于MindSpore复现Deeplabv3-语义分割 实验介绍 本实验主要介绍使用MindSpore深度学习框架在PASCAL VOC2012数据集上训练Deeplabv3网络模型.本实验使用了Mi ...
- 深度学习(二十一)基于FCN的图像语义分割-CVPR 2015-未完待续
CNN应用之基于FCN的图像语义分割 原文地址:http://blog.csdn.net/hjimce/article/details/50268555 作者:hjimce 一.相关理论 本篇 ...
- 语义分割——DeepLabv3+的学习笔记~
1 前言 听说DeepLabv3+是现在最优秀的语义分割框架~ 2 学习笔记 2.1 DeepLabv3+用到了CRF的技术吗? 没有,好像是通过增加context模块实现的:也就是利用了上下文的信息 ...
- FEANet——基于 RGBT的实时语义分割特征增强注意力网络
Overview Title:FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segment ...
- 三维(点云)语义分割概述以及方法总结
文章目录 -1. 语义分割 0. 三维表示的数据结构 0.1. Point cloud 0.2 3D voxel grids 0.3 collections of images/muti-view 0 ...
最新文章
- 框架之一:mybatis
- apeach和php合作原理,apache与php工作原理分析
- 计算机术语局部性,【计算机基础】程序的局部性简介
- 28岁程序员狂赚上亿宣布退休,网友:这就是命!
- 【Kafka】Kafka InvalidReceiveException: Invalid receive (size = 369296128 larger than 104857600)
- Java Web学习总结(3)——Servlet详解
- np.concatenate 函数的使用
- Remap 后的 USART1 不能发送数据
- Lucene实践之Query
- 【Codecs系列】视频格式国际标准:BT601/BT709/BT2020
- CU的递归划分详细介绍
- 七夕前夜,地球和月亮搭起“鹊桥”
- VS2022安装.Net Framework4.0方法
- 笔记本开热点自动断开
- 阿里开发手册 学习 记忆 理解 表达 融会贯通
- 上海证券交易所-债券品种介绍
- angular2后台管理系统
- 【数据分析】——分析方法
- 一种能人类大脑信息解读成声音信息的人工智能
- 《什么是HTML5》
热门文章
- 跨境电商如何玩转红人营销
- 2021年茶艺师(初级)考试题及茶艺师(初级)考试资料
- linux中rwrwr权限是多少,linux4_权限控制.ppt
- 支付宝错误 ALIN10146 排查
- Linux centos7 ubuntu 一键安装Java JDK 脚本 shell 脚本
- 二.求生之路2服务器的搭建(Windows)
- 雷电空战类游戏源代码
- python做购物车代码大全-python 字典实现简单购物车
- spring中 allowBeanDefinitionOverriding(spring.main.allow-bean-definition-overriding) 分析
- 国信长天嵌入式竞赛平台及扩展板硬件资源布局介绍