PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification
This work addresses a specific bottleneck in VI-ReID for security and surveillance applications, but it is incremental as it builds on existing part-based methods.
The paper tackles the problem of overfitting in part-based Visible-Infrared person Re-Identification (VI-ReID) models by introducing PartMix, a novel data augmentation technique that mixes part descriptors across modalities, resulting in consistent performance boosts when integrated into existing models.
Modern data augmentation using a mixture-based technique can regularize the models from overfitting to the training data in various computer vision applications, but a proper data augmentation technique tailored for the part-based Visible-Infrared person Re-IDentification (VI-ReID) models remains unexplored. In this paper, we present a novel data augmentation technique, dubbed PartMix, that synthesizes the augmented samples by mixing the part descriptors across the modalities to improve the performance of part-based VI-ReID models. Especially, we synthesize the positive and negative samples within the same and across different identities and regularize the backbone model through contrastive learning. In addition, we also present an entropy-based mining strategy to weaken the adverse impact of unreliable positive and negative samples. When incorporated into existing part-based VI-ReID model, PartMix consistently boosts the performance. We conduct experiments to demonstrate the effectiveness of our PartMix over the existing VI-ReID methods and provide ablation studies.