Real-world Person Re-Identification via Degradation Invariance Learning

04/10/2020
by   Yukun Huang, et al.
0

Person re-identification (Re-ID) in real-world scenarios usually suffers from various degradation factors, e.g., low-resolution, weak illumination, blurring and adverse weather. On the one hand, these degradations lead to severe discriminative information loss, which significantly obstructs identity representation learning; on the other hand, the feature mismatch problem caused by low-level visual variations greatly reduces retrieval performance. An intuitive solution to this problem is to utilize low-level image restoration methods to improve the image quality. However, existing restoration methods cannot directly serve to real-world Re-ID due to various limitations, e.g., the requirements of reference samples, domain gap between synthesis and reality, and incompatibility between low-level and high-level methods. In this paper, to solve the above problem, we propose a degradation invariance learning framework for real-world person Re-ID. By introducing a self-supervised disentangled representation learning strategy, our method is able to simultaneously extract identity-related robust features and remove real-world degradations without extra supervision. We use low-resolution images as the main demonstration, and experiments show that our approach is able to achieve state-of-the-art performance on several Re-ID benchmarks. In addition, our framework can be easily extended to other real-world degradation factors, such as weak illumination, with only a few modifications.

READ FULL TEXT

page 4

page 7

page 8

research
08/16/2019

Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification

Person re-identification (re-ID) aims at matching images of the same ide...
research
07/25/2019

Learning Resolution-Invariant Deep Representations for Person Re-Identification

Person re-identification (re-ID) solves the task of matching images acro...
research
09/16/2021

Resolution based Feature Distillation for Cross Resolution Person Re-Identification

Person re-identification (re-id) aims to retrieve images of same identit...
research
02/19/2020

Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond

Person re-identification (re-ID) aims at matching images of the same per...
research
01/23/2023

Illumination Variation Correction Using Image Synthesis For Unsupervised Domain Adaptive Person Re-Identification

Unsupervised domain adaptive (UDA) person re-identification (re-ID) aims...
research
08/03/2018

Learning Distributional Representation and Set Distance for Multi-shot Person Re-identification

Person re-identification aims to identify a specific person at distinct ...
research
02/11/2023

DaliID: Distortion-Adaptive Learned Invariance for Identification Models

In unconstrained scenarios, face recognition and person re-identificatio...

Please sign up or login with your details

Forgot password? Click here to reset