Learning Invariance from Generated Variance for Unsupervised Person Re-identification

01/02/2023
by   Hao Chen, et al.
0

This work focuses on unsupervised representation learning in person re-identification (ReID). Recent self-supervised contrastive learning methods learn invariance by maximizing the representation similarity between two augmented views of a same image. However, traditional data augmentation may bring to the fore undesirable distortions on identity features, which is not always favorable in id-sensitive ReID tasks. In this paper, we propose to replace traditional data augmentation with a generative adversarial network (GAN) that is targeted to generate augmented views for contrastive learning. A 3D mesh guided person image generator is proposed to disentangle a person image into id-related and id-unrelated features. Deviating from previous GAN-based ReID methods that only work in id-unrelated space (pose and camera style), we conduct GAN-based augmentation on both id-unrelated and id-related features. We further propose specific contrastive losses to help our network learn invariance from id-unrelated and id-related augmentations. By jointly training the generative and the contrastive modules, our method achieves new state-of-the-art unsupervised person ReID performance on mainstream large-scale benchmarks.

READ FULL TEXT

page 2

page 4

page 5

page 6

page 11

page 12

page 13

page 14

research
12/16/2020

Joint Generative and Contrastive Learning for Unsupervised Person Re-identification

Annotating identity labels in large-scale datasets is a labour-intensive...
research
06/15/2021

Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification

Unsupervised person re-identification (Re-ID) aims to match pedestrian i...
research
03/30/2021

ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification

Unsupervised person re-identification (ReID) aims at learning discrimina...
research
08/23/2021

Exploring the Quality of GAN Generated Images for Person Re-Identification

Recently, GAN based method has demonstrated strong effectiveness in gene...
research
06/11/2018

Semantically Selective Augmentation for Deep Compact Person Re-Identification

We present a deep person re-identification approach that combines semant...
research
06/05/2019

PAC-GAN: An Effective Pose Augmentation Scheme for Unsupervised Cross-View Person Re-identification

Person re-identification (person Re-Id) aims to retrieve the pedestrian ...
research
04/30/2019

Appearance and Pose-Conditioned Human Image Generation using Deformable GANs

In this paper, we address the problem of generating person images condit...

Please sign up or login with your details

Forgot password? Click here to reset