PMC-GANs: Generating Multi-Scale High-Quality Pedestrian with Multimodal Cascaded GANs
arXiv:1912.12799
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 (17)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Auto-Encoding Variational Bayes
- Conditional Generative Adversarial Nets
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Adversarial Feature Learning
- Adversarially Learned Inference
- Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
- FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks
- BAGAN: Data Augmentation with Balancing GAN
- Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
- Progressive Pose Attention Transfer for Person Image Generation
- Repulsion Loss: Detecting Pedestrians in a Crowd
- Unsupervised Person Image Generation with Semantic Parsing Transformation
- Learning to Generate Synthetic Data via Compositing