WeditGAN: Few-Shot Image Generation via Latent Space Relocation
In few-shot image generation, directly training GAN models on just a handful of images faces the risk of overfitting. A popular solution is to transfer the models pretrained on large source domains to small target ones. In this work, we introduce WeditGAN, which realizes model transfer by editing the intermediate latent codes $w$ in StyleGANs with learned constant offsets ($\Delta w$), discovering and constructing target latent spaces via simply relocating the distribution of source latent spaces. The established one-to-one mapping between latent spaces can naturally prevents mode collapse and overfitting. Besides, we also propose variants of WeditGAN to further enhance the relocation process by regularizing the direction or finetuning the intensity of $\Delta w$. Experiments on a collection of widely used source/target datasets manifest the capability of WeditGAN in generating realistic and diverse images, which is simple yet highly effective in the research area of few-shot image generation. Codes are available at https://github.com/Ldhlwh/WeditGAN.
Code (1)
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
Where Is My Spot? Few-Shot Image Generation via Latent Subspace Optimization
Image generation relies on massive training data that can hardly produce diverse images of an unseen category according to a few examples. In this paper, we address this dilemma by projecting sparse few-shot samples …
Image GenerationCross-Linked Variational Autoencoders for Generalized Zero-Shot Learning
Most approaches in generalized zero-shot learning rely on cross-modal mapping between an image feature space and a class embedding space or on generating artificial image features. However, learning a shared cross-modal …
Few-Shot LearningGeneralized Zero-Shot LearningZero-Shot LearningGeneralized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by gen…
Few-Shot LearningGeneralized Few-Shot LearningGeneralized Zero-Shot LearningZero-Shot Learning+1Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space. As labeled images are expensive, one direction is to augment the dataset by gen…
Few-Shot LearningGeneralized Few-Shot LearningGeneralized Zero-Shot LearningGeneralized Zero-Shot Learning - Unseen+2Norm-guided latent space exploration for text-to-image generation
Text-to-image diffusion models show great potential in synthesizing a large variety of concepts in new compositions and scenarios. However, the latent space of initial seeds is still not well understood and its structure…
Image GenerationLong-tail LearningText to Image GenerationText-to-Image Generation