RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
This work addresses a domain-specific challenge in computer vision for security and surveillance applications, offering a novel joint alignment approach that is incremental over prior feature-only methods.
The paper tackles the problem of RGB-Infrared person re-identification by proposing AlignGAN, a model that jointly uses pixel and feature alignment to bridge cross-modality variations, achieving absolute gains of 15.4% in Rank-1 and 12.9% in mAP on the SYSU-MM01 dataset.
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.