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

5 Apr 2018  ·  Xi Ouyang, Yu Cheng, Yifan Jiang, Chun-Liang Li, Pan Zhou ·

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.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Scene Text Recognition MSDA MLDG Average Accuracy 19.02% # 2

Methods


No methods listed for this paper. Add relevant methods here