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

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.

Accepted by The British Machine Vision Conference (BMVC2019)

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Progressive Pose Attention Transfer for Person Image Generation
• Unsupervised Person Image Generation with Semantic Parsing Transformation
• Learning to Generate Synthetic Data via Compositing

Cited by in corpus (1)

• Progressive and Aligned Pose Attention Transfer for Person Image Generation