Joint Discriminative and Generative Learning for Person Re-identification

04/15/2019
by   Zhedong Zheng, et al.
20

Person re-identification (re-id) remains challenging due to significant intra-class variations across different cameras. Recently, there has been a growing interest in using generative models to augment training data and enhance the invariance to input changes. The generative pipelines in existing methods, however, stay relatively separate from the discriminative re-id learning stages. Accordingly, re-id models are often trained in a straightforward manner on the generated data. In this paper, we seek to improve learned re-id embeddings by better leveraging the generated data. To this end, we propose a joint learning framework that couples re-id learning and data generation end-to-end. Our model involves a generative module that separately encodes each person into an appearance code and a structure code, and a discriminative module that shares the appearance encoder with the generative module. By switching the appearance or structure codes, the generative module is able to generate high-quality cross-id composed images, which are online fed back to the appearance encoder and used to improve the discriminative module. The proposed joint learning framework renders significant improvement over the baseline without using generated data, leading to the state-of-the-art performance on several benchmark datasets.

READ FULL TEXT

page 1

page 3

page 6

page 7

page 12

research
07/20/2020

Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification

Although a significant progress has been witnessed in supervised person ...
research
05/07/2020

End-to-End Domain Adaptive Attention Network for Cross-Domain Person Re-Identification

Person re-identification (re-ID) remains challenging in a real-world sce...
research
03/23/2018

Pose-Driven Deep Models for Person Re-Identification

Person re-identification (re-id) is the task of recognizing and matching...
research
10/22/2021

Local-Global Associative Frame Assemble in Video Re-ID

Noisy and unrepresentative frames in automatically generated object boun...
research
03/07/2016

Learning a Discriminative Null Space for Person Re-identification

Most existing person re-identification (re-id) methods focus on learning...
research
09/24/2020

FTN: Foreground-Guided Texture-Focused Person Re-Identification

Person re-identification (Re-ID) is a challenging task as persons are of...
research
05/05/2019

Intra-clip Aggregation for Video Person Re-identification

Video-based person re-id has drawn much attention in recent years due to...

Please sign up or login with your details

Forgot password? Click here to reset