Beyond View Transformation: Cycle-Consistent Global and Partial Perception Gan for View-Invariant Gait Recognition

Shuangqun Li, Wu Liu, Huadong Ma, Shaopeng Zhu

Abstract

Cross-view gait recognition is a challenging problem when view-interval and pose variation are relatively large. In this paper, we propose Cycle-consistent Attentive Generative Adversarial Networks (CA-GAN) to map different views' gait images to view-consistent and photorealistic gait images for cross-view gait recognition. In CA-GAN, the generative network is composed of two branches, which simultaneously perceives human's global contexts and local body parts information respectively. Moreover, we design a novel Attentive Adversarial Network (AAN) to adaptively learn different weights for the discriminator's receptive fields with attention mechanism. Furthermore, as it is hard to collect the pose-aligned gait image pairs from different views for training CA-GAN’ we combine forward cycle-consistency loss and adver-sarial loss to learn the transformation relationship from source views to target view. The combined loss function can also preserve the discriminative gait structures of different identities at the training stage. Finally, we directly exploit the synthesized view-consistent gait images for cross-view gait recognition task. Experimental results on CASIA-B demonstrate that our method not only outperforms the state-of-the-art methods in cross-view gait recognition, but also presents compelling perceptual results even across the large view-interval.
BibTeX
@inproceedings{li2018beyond,
  author = {Shuangqun Li and Wu Liu and Huadong Ma and Shaopeng Zhu},
  title = {{Beyond View Transformation: Cycle-Consistent Global and Partial Perception Gan for View-Invariant Gait Recognition}},
  booktitle = {ICME},
  year = {2018},
  doi = {10.1109/icme.2018.8486484},
}

Loading related content...

Figure