SFANet: A Spectrum-aware Feature Augmentation Network for Visible-Infrared Person Re-Identification

02/24/2021
by   Haojie Liu, et al.
10

Visible-Infrared person re-identification (VI-ReID) is a challenging matching problem due to large modality varitions between visible and infrared images. Existing approaches usually bridge the modality gap with only feature-level constraints, ignoring pixel-level variations. Some methods employ GAN to generate style-consistent images, but it destroys the structure information and incurs a considerable level of noise. In this paper, we explicitly consider these challenges and formulate a novel spectrum-aware feature augementation network named SFANet for cross-modality matching problem. Specifically, we put forward to employ grayscale-spectrum images to fully replace RGB images for feature learning. Learning with the grayscale-spectrum images, our model can apparently reduce modality discrepancy and detect inner structure relations across the different modalities, making it robust to color variations. In feature-level, we improve the conventional two-stream network through balancing the number of specific and sharable convolutional blocks, which preserve the spatial structure information of features. Additionally, a bi-directional tri-constrained top-push ranking loss (BTTR) is embedded in the proposed network to improve the discriminability, which efficiently further boosts the matching accuracy. Meanwhile, we further introduce an effective dual-linear with batch normalization ID embedding method to model the identity-specific information and assits BTTR loss in magnitude stabilizing. On SYSU-MM01 and RegDB datasets, we conducted extensively experiments to demonstrate that our proposed framework contributes indispensably and achieves a very competitive VI-ReID performance.

READ FULL TEXT

page 1

page 3

page 4

page 9

page 11

page 12

research
04/11/2022

Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification

Visible-infrared person re-identification (VI-ReID) is a challenging and...
research
07/23/2019

Enhancing the Discriminative Feature Learning for Visible-Thermal Cross-Modality Person Re-Identification

Existing person re-identification has achieved great progress in the vis...
research
07/15/2019

An Efficient Framework for Visible-Infrared Cross Modality Person Re-Identification

Visible-infrared cross modality person re-identification (VI-ReId) is an...
research
06/01/2020

Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification

RGB-Infrared person re-identification (RGB-IR ReID) is a cross-modality ...
research
02/29/2020

Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identification

Due to its potential wide applications in video surveillance and other c...
research
02/03/2023

Spectral Aware Softmax for Visible-Infrared Person Re-Identification

Visible-infrared person re-identification (VI-ReID) aims to match specif...
research
08/01/2022

Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification

Graph-based models have achieved great success in person re-identificati...

Please sign up or login with your details

Forgot password? Click here to reset