2019/10/13 by Guan’an Wang, Guan'an Wang, Wang, Guan'an +11 · 59 citations
Computer Science · #Advanced Neural Network Applications #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Discriminator #FOS: Computer and information sciences #Face recognition and analysis #Feature (linguistics) #Feature learning #Generator (circuit theory) #Modality (human–computer interaction) #Pattern recognition (psychology) #Pixel #RGB color model #Video Surveillance and Tracking Methods #cs.CV
paper · pdf · doi:10.48550/arxiv.1910.05839
published in arXiv (Cornell University) 2019, 3622-3631 (Cornell University) · accepted by ICCV'19
openalex publication_date 2019/10/13 · arxiv created 2019/10/28 · arxiv updated 2019/10/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
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 favorably 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.