RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment

By Guan'an Wang, Tianzhu Zhang, Jian Cheng, Si Liu, Yang Yang, Zeng-Huang Hou. IEEE International Conference on Computer Vision, 2019

477 citations recorded by the source corpus.

RGB-Infrared (IR) person re-identification is an important and challenging task due to large cross-modality variations between RGB and IR images. Most conventional approaches aim to bridge the cross-modality gap with feature alignment by feature representation learning. Different from existing methods, in this paper, we propose a novel and end-to-end Alignment Generative Adversarial Network (AlignGAN) for the RGB-IR RE-ID task. The proposed model enjoys several merits. First, it can exploit pixel alignment and feature alignment jointly. To the best of our knowledge, this is the first work to model the two alignment strategies jointly for the RGB-IR RE-ID problem. Second, the proposed model consists of a pixel generator, a feature generator and a joint discriminator. By playing a min-max game among the three components, our model is able to not only alleviate the cross-modality and intra-modality variations, but also learn identity-consistent features. Extensive experimental results on two standard benchmarks demonstrate that the proposed model performs favourably against state-of-the-art methods. Especially, on SYSU-MM01 dataset, our model can achieve an absolute gain of 15.4% and 12.9% in terms of Rank-1 and mAP.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/458a741db61a78301ae70b616704d9209c9f7996

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

Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer (2021, unknown): “Recently, person Re-ID has drawn a growing amount of interest from academia and industry, and various methods have been proposed [20, 24, 14, 38, 18, 27, 42, 43].”
Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification (2020, methodology): “Note that AlignGAN [44] represents the state-of-the-art by aligning the features in both the feature level and pixel level with generated 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 ] .”
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].”
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.”
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): “The training/testing split procedure is repeated ten times [33, 36, 51], Table 1.”
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).”
High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification (2020, methodology): “Existing methods can be grouped into hand-crafted descriptors [25, 39, 18], metric learning methods [44, 16, 19] and deep learning algorithms [43, 11, 35, 36, 37, 22].”