Unsupervised Attention Based Instance Discriminative Learning for Person Re-Identification

11/03/2020
by   Kshitij Nikhal, et al.
0

Recent advances in person re-identification have demonstrated enhanced discriminability, especially with supervised learning or transfer learning. However, since the data requirements—including the degree of data curations—are becoming increasingly complex and laborious, there is a critical need for unsupervised methods that are robust to large intra-class variations, such as changes in perspective, illumination, articulated motion, resolution, etc. Therefore, we propose an unsupervised framework for person re-identification which is trained in an end-to-end manner without any pre-training. Our proposed framework leverages a new attention mechanism that combines group convolutions to (1) enhance spatial attention at multiple scales and (2) reduce the number of trainable parameters by 59.6 framework jointly optimizes the network with agglomerative clustering and instance learning to tackle hard samples. We perform extensive analysis using the Market1501 and DukeMTMC-reID datasets to demonstrate that our method consistently outperforms the state-of-the-art methods (with and without pre-trained weights).

READ FULL TEXT

page 1

page 4

page 8

research
07/21/2020

Learning Person Re-identification Models from Videos with Weak Supervision

Most person re-identification methods, being supervised techniques, suff...
research
06/24/2018

Attention-based Few-Shot Person Re-identification Using Meta Learning

In this paper, we investigate the challenging task of person re-identifi...
research
08/21/2020

An Improved Person Re-identification Method by light-weight convolutional neural network

Person Re-identification is defined as a recognizing process where the p...
research
06/04/2019

Towards better Validity: Dispersion based Clustering for Unsupervised Person Re-identification

Person re-identification aims to establish the correct identity correspo...
research
01/16/2018

Re-ID done right: towards good practices for person re-identification

Training a deep architecture using a ranking loss has become standard fo...
research
10/03/2020

End-to-End Training of CNN Ensembles for Person Re-Identification

We propose an end-to-end ensemble method for person re-identification (R...
research
05/28/2017

Person Depth ReID: Robust Person Re-identification with Commodity Depth Sensors

This work targets person re-identification (ReID) from depth sensors suc...

Please sign up or login with your details

Forgot password? Click here to reset