Hetero-Center Loss for Cross-Modality Person Re-Identification

10/22/2019
by   Yuanxin Zhu, et al.
17

Cross-modality person re-identification is a challenging problem which retrieves a given pedestrian image in RGB modality among all the gallery images in infrared modality. The task can address the limitation of RGB-based person Re-ID in dark environments. Existing researches mainly focus on enlarging inter-class differences of feature to solve the problem. However, few studies investigate improving intra-class cross-modality similarity, which is important for this issue. In this paper, we propose a novel loss function, called Hetero-Center loss (HC loss) to reduce the intra-class cross-modality variations. Specifically, HC loss can supervise the network learning the cross-modality invariant information by constraining the intra-class center distance between two heterogenous modalities. With the joint supervision of Cross-Entropy (CE) loss and HC loss, the network is trained to achieve two vital objectives, inter-class discrepancy and intra-class cross-modality similarity as much as possible. Besides, we propose a simple and high-performance network architecture to learn local feature representations for cross-modality person re-identification, which can be a baseline for future research. Extensive experiments indicate the effectiveness of the proposed methods, which outperform state-of-the-art methods by a wide margin.

READ FULL TEXT

page 1

page 5

page 10

page 15

research
09/12/2023

Modality Unifying Network for Visible-Infrared Person Re-Identification

Visible-infrared person re-identification (VI-ReID) is a challenging tas...
research
04/01/2021

DF^2AM: Dual-level Feature Fusion and Affinity Modeling for RGB-Infrared Cross-modality Person Re-identification

RGB-infrared person re-identification is a challenging task due to the i...
research
10/21/2021

MSO: Multi-Feature Space Joint Optimization Network for RGB-Infrared Person Re-Identification

The RGB-infrared cross-modality person re-identification (ReID) task aim...
research
06/07/2019

HPILN: A feature learning framework for cross-modality person re-identification

Most video surveillance systems use both RGB and infrared cameras, makin...
research
02/02/2023

Exploring Invariant Representation for Visible-Infrared Person Re-Identification

Cross-spectral person re-identification, which aims to associate identit...
research
08/28/2019

Orthogonal Center Learning with Subspace Masking for Person Re-Identification

Person re-identification aims to identify whether pairs of images belong...
research
07/03/2020

A Similarity Inference Metric for RGB-Infrared Cross-Modality Person Re-identification

RGB-Infrared (IR) cross-modality person re-identification (re-ID), which...

Please sign up or login with your details

Forgot password? Click here to reset