深度学习re-id综述

特征提取

global feature

借助人体图像分割

Human Semantic Parsing for Person Re-identification CVPR2018
把人体图像分割成几个部分做attention

多尺寸

Multi-scale Deep Learning Architectures for Person Re-identification ICCV2017
手工设计多尺度的inception流

Attention

1. Harmonious AttentionCNN(HA-CNN)CVPR2018
   软注意力(channel+spatial)+硬注意力（指导local brach）
   

local feature

人体部分/区域特征的集合，解决对齐问题，身体部分由人体姿态构建或者粗略的垂直分割完成

Auxilary 辅助方法

需要额外的标注信息

• 语意属性标注
• view
  View Confusion Feature Learning for Person Re-identification
  ICCV2019
  通过分类器得到view信息，然后通过分类器对抗损失、视觉feature损失、sift损失迫使提取出viewpoint invariant的feature
  
• camera
• data augumentation

1. 位姿约束
   
   guild 指导符合原来的分类

2. 相机风格信息
   
   camstyle

3. 将外观和结构分离生成图片
   

4. 无监督域适应
   
   SPGAN eSPGAN

Person Transfer GAN to Bridge Domain Gap for Person Re-Identification- PTGAN
Wei et al. [35] handle the domain
gap problem by proposing a Person Transfer Generative
Adversarial Network (PTGAN), transferring the knowledge
from one labeled source dataset to another unlabeled target
dataset.
An image-image domain adaptation method [118]
is developed with preserved self-similarity and domaindissimilarity, trained with a similarity preserving generative adversarial network (SPGAN).
A Hetero-Homogeneous Learning (HHL) method [215] simultaneously considers the
camera invariance with homogeneous learning (image pairs
from the same domain) and domain connectedness with
heterogeneous learning (cross-domain negative pairs).

• 网络结构
  OmniScale Network (OSNet) 多尺度

Multi-Level Factorisation Net (MLFN) 多层级

度量函数

• identity loss 分类损失
  
• varification loss
  区分这一对图片是否是同一个人
  
• triplet loss
  

优化方法

re-ranking 使用gallery-to-gallery 的相似性来优化初始序列。

待解决问题

Scalable Re-ID

• Lightweight Model. 更轻型的结构、模型蒸馏
• Resource Aware Re-ID.根据硬件配置适应性地调整模型 Deep Anytime ReID (DaRe)

Domain-Specific Architecture Design

多基于分类网络，为re-id网络提出新的结构

related work

• 多尺度网络 参数过多
  1.另外加局部特征分支
  

2. 使用多尺度的卷积流
   OSnet

• 多层级

1. 使用附加的属性信息
   
2. 融合多层信息
   
3. deep supervision