google/lecam-gan
Regularizing Generative Adversarial Networks under Limited Data (CVPR 2021)
This project helps researchers and practitioners in computer vision to generate realistic synthetic images, especially when they have only a small amount of real image data for training. It takes existing image datasets, even small ones, and improves the quality and diversity of the generated images. This is useful for computer vision engineers, researchers, and machine learning scientists working on image synthesis and generation tasks.
166 stars. No commits in the last 6 months.
Use this if you are developing AI models that generate images and are struggling with obtaining high-quality results due to a scarcity of training images.
Not ideal if you are looking for a general-purpose image editing tool or a solution for image classification or object detection.
Stars
166
Forks
16
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
May 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/google/lecam-gan"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yunjey/domain-transfer-network
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
taesungp/contrastive-unpaired-translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV...
PaddlePaddle/PaddleGAN
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion...
tohinz/ConSinGAN
PyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)
sagiebenaim/DistanceGAN
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017