One-Shot Image-to-Image Translation via Part-Global Learning with a Multi-adversarial Framework
arXiv:1905.04729
Abstract
It is well known that humans can learn and recognize objects effectively from several limited image samples. However, learning from just a few images is still a tremendous challenge for existing main-stream deep neural networks. Inspired by analogical reasoning in the human mind, a feasible strategy is to translate the abundant images of a rich source domain to enrich the relevant yet different target domain with insufficient image data. To achieve this goal, we propose a novel, effective multi-adversarial framework (MA) based on part-global learning, which accomplishes one-shot cross-domain image-to-image translation. In specific, we first devise a part-global adversarial training scheme to provide an efficient way for feature extraction and prevent discriminators being over-fitted. Then, a multi-adversarial mechanism is employed to enhance the image-to-image translation ability to unearth the high-level semantic representation. Moreover, a balanced adversarial loss function is presented, which aims to balance the training data and stabilize the training process. Extensive experiments demonstrate that the proposed approach can obtain impressive results on various datasets between two extremely imbalanced image domains and outperform state-of-the-art methods on one-shot image-to-image translation.
arXiv comment9 pages, 13 figures
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- 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
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Matching Networks for One Shot Learning
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
- Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
- MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
- One-Shot Unsupervised Cross Domain Translation
- Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs
- Generative Adversarial Network with Multi-Branch Discriminator for Cross-Species Image-to-Image Translation