Uniform Light Transformer for Person Re-Identiffcation Under Complex Illumination

Abstract

We explored using a Uniffed Lighting Transformer for pedestrian image retrieval under varying illumination conditions compared with the one-to-one method. We discovered that the modeling capability of the Uniffed Lighting Transformer for low-frequency information decreases gradually with an increase in the number of illuminant variations. Therefore, based on this insight, we proposed a Discriminative Feature Spectrum Consistency and Low-Frequency information-constrained method. This method employs two constraints to enhance the Uniffed Lighting Transformer’s modeling capability for low-frequency information. The ffrst mechanism enforces the constraint at the feature level by comparing the spectrum information between real and fake discriminative features. The second approach constrains the differences in pedestrian recognition features caused by the differences in low-frequency information between real and virtual images composed of low-frequency information from fake images and high-frequency information from authentic images. Experiments demonstrate that our method outperforms other approaches and performs best across all metrics.

Keywords: Person re-identification, generative adversarial network, illumination-adaptive.