Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond

TL;DR

This paper introduces Pedestrian-Synthesis-GAN, a novel generative model that creates realistic pedestrian images with background context, aiding in training better pedestrian detection models without extensive manual annotation.

Contribution

The paper presents a GAN-based framework with multiple discriminators and spatial pyramid pooling to synthesize realistic pedestrian data for detector training, reducing annotation efforts.

Findings

Synthesized pedestrians improve detector performance

Framework generates realistic pedestrian images with background context

Effective across various background variations

Abstract

State-of-the-art pedestrian detection models have achieved great success in many benchmarks. However, these models require lots of annotation information and the labeling process usually takes much time and efforts. In this paper, we propose a method to generate labeled pedestrian data and adapt them to support the training of pedestrian detectors. The proposed framework is built on the Generative Adversarial Network (GAN) with multiple discriminators, trying to synthesize realistic pedestrians and learn the background context simultaneously. To handle the pedestrians of different sizes, we adopt the Spatial Pyramid Pooling (SPP) layer in the discriminator. We conduct experiments on two benchmarks. The results show that our framework can smoothly synthesize pedestrians on background images of variations and different levels of details. To quantitatively evaluate our approach, we add the generated samples into training data of the baseline pedestrian detectors and show the synthetic images are able to improve the detectors' performance.