MatchingGAN: Matching-based Few-shot Image Generation
This addresses the challenge of expensive data acquisition for image generation in few-shot settings, though it appears incremental as an extension of GANs with matching mechanisms.
The paper tackles the problem of generating new images for a category with only a few training examples by proposing MatchingGAN, which uses a matching generator and discriminator to fuse features from conditional images, achieving effective results as demonstrated on three datasets.
To generate new images for a given category, most deep generative models require abundant training images from this category, which are often too expensive to acquire. To achieve the goal of generation based on only a few images, we propose matching-based Generative Adversarial Network (GAN) for few-shot generation, which includes a matching generator and a matching discriminator. Matching generator can match random vectors with a few conditional images from the same category and generate new images for this category based on the fused features. The matching discriminator extends conventional GAN discriminator by matching the feature of generated image with the fused feature of conditional images. Extensive experiments on three datasets demonstrate the effectiveness of our proposed method.