Dynamic Label Graph Matching for Unsupervised Video Re-Identification

09/27/2017
by   Mang Ye, et al.
0

Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models. Specifically, we propose to construct a graph for samples in each camera, and then graph matching scheme is introduced for cross-camera labeling association. While labels directly output from existing graph matching methods may be noisy and inaccurate due to significant cross-camera variations, this paper proposes a dynamic graph matching (DGM) method. DGM iteratively updates the image graph and the label estimation process by learning a better feature space with intermediate estimated labels. DGM is advantageous in two aspects: 1) the accuracy of estimated labels is improved significantly with the iterations; 2) DGM is robust to noisy initial training data. Extensive experiments conducted on three benchmarks including the large-scale MARS dataset show that DGM yields competitive performance to fully supervised baselines, and outperforms competing unsupervised learning methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 8

research
03/08/2021

Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification

This paper considers the problem of unsupervised person re-identificatio...
research
08/27/2017

Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification

While metric learning is important for Person re-identification (RE-ID),...
research
08/22/2018

Deep Association Learning for Unsupervised Video Person Re-identification

Deep learning methods have started to dominate the research progress of ...
research
02/12/2020

Towards Precise Intra-camera Supervised Person Re-identification

Intra-camera supervision (ICS) for person re-identification (Re-ID) assu...
research
05/06/2022

A High-Accuracy Unsupervised Person Re-identification Method Using Auxiliary Information Mined from Datasets

Supervised person re-identification methods rely heavily on high-quality...
research
09/28/2015

Theoretical Analysis of the Optimal Free Responses of Graph-Based SFA for the Design of Training Graphs

Slow feature analysis (SFA) is an unsupervised learning algorithm that e...
research
03/29/2022

Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification

To learn camera-view invariant features for person Re-IDentification (Re...

Please sign up or login with your details

Forgot password? Click here to reset