[Paper note] Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification

  • Author: Rahul Rama Varior, NTU Singapore; Mrinal Haloi, Nanyang technological Universi; Gang Wang
  • Picutre of the model

2016_10_14_cebff7ce866e92a1c89e96dfc777d19

Contribution

  1. Architecture of baseline siamese network for person re-id.
  2. Matching gate between convolutional blocks.

Matching gate (MG) structure

  • Feature summarization
    • Aggregates the local feature along a horizontal stripe.
    • Deal with problem of changed view point (view point change in re-id typically in the horizontal direction, same parts are very likely to be along the same horizontal region).
    • Equation and dimention:
      equation; equation
      where equation is the equation row of feature map. equation (maybe equation) and equation (maybe equation).
  • Feature similarity
    • Euclidean distance of equation and equation
      equation
      where equation
    • equation decides the variance of the Gaussian function, learnable, should set a higher initial value.
  • Filtering and boosting the features
    • Repeat equation c times horizontally to obtain equation.
    • Add filtered feature to original feature.
      equation
      equation
    • Perform L2 normalization across channels after this

Result

  • Dataset: Market-1501, CUHK-03, VIPeR.
  • Baseline S-CNN outperform most CNN approaches. With MG gaining further improvement.
  • Visualization of gate. Low gate activation means low similarity.
    2016_10_14_abc0a52873dfd63db5fbe8ad154b87c
  • 3
    点赞
  • 2
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值