paper-with-me

홈 › Papers

WeditGAN: Few-Shot Image Generation via Latent Space Relocation

2023-05-11 · Yuxuan Duan, Li Niu, Yan Hong, Liqing Zhang

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.

📄 PDF Abstract BibTeX arXiv:2305.06671

Code (1)

ldhlwh/weditgan 공식 구현 pytorch

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Where Is My Spot? Few-Shot Image Generation via Latent Subspace Optimization

2023-01-01 · CVPR 2023 1 · Chenxi Zheng, Bangzhen Liu, Huaidong Zhang, Xuemiao Xu 외

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 Generation

Cross-Linked Variational Autoencoders for Generalized Zero-Shot Learning

2019-03-24 · ICLR Workshop LLD 2019 · Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell 외

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 Learning

Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders

2018-12-05 · Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell 외

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+1

Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders

2019-06-01 · CVPR 2019 6 · Edgar Schonfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell 외

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+2

Norm-guided latent space exploration for text-to-image generation

2023-06-14 · NeurIPS 2023 11 · Dvir Samuel, Rami Ben-Ari, Nir Darshan, Haggai Maron 외

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