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

TL;DR

This paper introduces PMC-GANs, a cascaded multi-scale GAN model that generates high-quality, diverse pedestrian images to enhance data augmentation for pedestrian detection tasks.

Contribution

The paper presents a novel cascaded multi-scale GAN architecture with residual U-net and attention blocks for realistic pedestrian image synthesis.

Findings

PMC-GANs outperforms baseline models in image quality.

Data augmentation with PMC-GANs improves pedestrian detection accuracy.

The model effectively generates high-resolution, diverse pedestrian images.

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.