weixin_56836871的博客

引言DeepLab系列在语义分割领域是比较经典的模型，整个系统从v1演进到v3+，可以看到作者在各个版本间使用的改进技术，从中可以看到在语义分割领域各个子问题是如何改进&模型的技术演进思路。DeepLabV1–SEMANTIC IMAGE SEGMENTATION WITH DEEP CONVOLUTIONAL NETS AND FULLY CONNECTED CRFS （2015）问题&解决思路There are two technical hurdles in the app

动机：Is it possible to build a scalable detection architecture with both higher accuracy and better efficiency across a wide spectrum of resource constraints (e.g., from 3B to 300B FLOPs)?【CC】开门见山：基于不同的算力构建一族网络We systematically study neural network archit

动机：in this paper that predicts a 3D bounding box for each detected object by combining a single keypoint estimate with regressed 3D variables. As a second contribution, we propose a multi-step disentangling approach for constructing the 3D bounding box, w

背景知识：Vector of Locally Aggregated Descriptors（VLAD）image retrieval.【CC】是广泛使用的图像提取方式，本文是在在这个提取器上做改进；具体是啥下面有介绍weakly supervised ranking loss【CC】本文的另外一个创新点是弱监督的LOSS设计，后面有介绍Place recongnition as an instance retrieval task：the query image location is estim

动机：对3D-LaneNet的改进； 特点 semi-local tile representation： breaks down lanes into simple lane segments whose parameters can be learnt【CC】网格化，基于每个网格去学习Lane的特征；最后再通过NN合起来；这样天然就是Anchorfree的，并且支持不规则的/没有封闭的曲线技术点：3D-LaneNet： The first is a CNN architecture wi

动机In this paper we develop a one-stage detector and forecaster that exploits both 3D point clouds produced by a LiDAR sensor as well as dynamic maps of the environment.we exploit 3D LiDAR point clouds and dynamic HD maps containing semantic elements such

动机本文通过一个不深的网络搞定了3D的目标检测/跟踪/预测。采用BEV的方式进行表达。猜测本文是MP3论文关于Perception部分的原型。输入：4D张量（X,Y,Z,T）输出：备忘This can result in catastrophic failures as downstream processes cannot recover from errors that appear at the beginning of the pipeline– 级联方式下后端处理模块无法修正千点模

文章来源：文章意义&解决的问题：相关概念：文章创新点：网络结构：