PMC-GANs: Generating Multi-Scale High-Quality Pedestrian with Multimodal Cascaded GANs

Jie Wu (China Electronics Technology Cyber Security Co., Ltd.), Ying Peng (China Electronics Technology Cyber Security Co., Ltd.), Chenghao Zheng (China Electronics Technology Cyber Security Co., Ltd.), Zongbo Hao (UESTC), Zhang Jian (China Electronics Technology Cyber Security Co., Ltd)

Abstract
Recently, generative adversarial networks (GANs) have shown great advantages in synthesizing images, leading to a boost of explorations of using faked images to augment data. This paper proposes a multimodal cascaded generative adversarial networks (PMC-GANs) to generate realistic and diversified pedestrian images and augment pedestrian detection data. The generator of our model applies a residual U-net structure, with multi-scale residual blocks to encode features, and attention residual blocks to help decode and rebuild pedestrian images. The model constructs in a coarse-to-fine fashion and adopts cascade structure, which is beneficial to produce high-resolution pedestrians. PMC-GANs outperforms baselines, and when used for data augmentation, it improves pedestrian detection results.

DOI
10.5244/C.33.157
https://dx.doi.org/10.5244/C.33.157

Files
Paper (PDF)

BibTeX