Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification

By Zhixiang Wang, Yinqiang Zheng, Yung-Yu Chuang, S. Satoh. Computer Vision and Pattern Recognition, 2019

440 citations recorded by the source corpus.

Infrared-Visible person RE-IDentification (IV-REID) is a rising task. Compared to conventional person re-identification (re-ID), IV-REID concerns the additional modality discrepancy originated from the different imaging processes of spectrum cameras, in addition to the person's appearance discrepancy caused by viewpoint changes, pose variations and deformations presented in the conventional re-ID task. The co-existed discrepancies make IV-REID more difficult to solve. Previous methods attempt to reduce the appearance and modality discrepancies simultaneously using feature-level constraints. It is however difficult to eliminate the mixed discrepancies using only feature-level constraints. To address the problem, this paper introduces a novel Dual-level Discrepancy Reduction Learning (D$^2$RL) scheme which handles the two discrepancies separately. For reducing the modality discrepancy, an image-level sub-network is trained to translate an infrared image into its visible counterpart and a visible image to its infrared version. With the image-level sub-network, we can unify the representations for images with different modalities. With the help of the unified multi-spectral images, a feature-level sub-network is trained to reduce the remaining appearance discrepancy through feature embedding. By cascading the two sub-networks and training them jointly, the dual-level reductions take their responsibilities cooperatively and attentively. Extensive experiments demonstrate the proposed approach outperforms the state-of-the-art methods.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3f9c2de56950ece198bb6e550e8ab87242d7b256

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification (2019, methodology): “More recent research [31] has attempted to bridge the cross-modality gap using an imagelevel constraint.”
Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification (2020, methodology): “Recently, many deep ReID methods (Zheng, Yang, and Hauptmann 2016; Hermans, Beyer, and Leibe 2017; Wang et al. 2019a) have been proposed.”
Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer (2020, methodology): “In this subsection, we compare our proposed algorithm with the baselines as well as the state-of-the-art methods, including Zero-Padding [46], TONE [49], BDTR [50], cmGAN [4], D(2)RL[44], MSR[7], D-HSME[13], IPVT[19] and AlignGAN[42].”
Infrared-Visible Cross-Modal Person Re-Identification with an X Modality (2020, methodology): “For statistically stable results, the evaluation procedure is repeated for 10 trials with randomly sampled query and gallery sets, as (Ye et al. 2018a; Feng, Lai, and Xie 2019; Wang et al. 2019c).”
Deep Learning for Person Re-Identification: A Survey and Outlook (2020, methodology): “Recent methods [194], [195] adopt the GAN technique to generate cross-modality person images to reduce the cross-modality discrepancy at both image and feature level.”
Channel Augmented Joint Learning for Visible-Infrared Recognition (2021, methodology): “We observe that the channel augmented images share similar visual appearance with the infrared images 1 The two modalities may share the same feature network, as in [7, 36]. while maintaining the original texture structure of the visible images.”
Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registration (2022, methodology): “These obstacles gave rise to the development of cross-modality medical image translation [ Yang et al. , 2020; Liu et al. , 2020a; Liu et al. , 2021d ] and cross-modality Re-ID tasks [ Wang et al. , 2019a; Wang et al. , 2019b ] .”