Efficient GAN

Efficient GANs aim to reduce the substantial computational demands of Generative Adversarial Networks (GANs) while maintaining or improving generative quality. Current research focuses on techniques like knowledge distillation, network pruning (especially structured pruning of U-Net architectures), and patch-based training to achieve this efficiency, often incorporating elements like wavelet transforms or semi-supervised learning. These advancements are significant because they enable the deployment of high-performing GANs in resource-constrained environments and accelerate training and inference times for various applications, including image binarization, image-to-image translation, and skin lesion segmentation.

Papers

July 5, 2024

Efficient GANs for Document Image Binarization Based on DWT and Normalization
Rui-Yang Ju, KokSheik Wong, Jen-Shiun Chiang
Generative Adversarial Network Normalization Dictionary Document Image Binarization Efficient GAN

May 19, 2024

Nickel and Diming Your GAN: A Dual-Method Approach to Enhancing GAN Efficiency via Knowledge Distillation
Sangyeop Yeo, Yoojin Jang, Jaejun Yoo
Generative Adversarial Network Knowledge Distillation GAN Model Network Compression Generative Quality Dual Approach Efficient GAN

September 17, 2023

UGC: Unified GAN Compression for Efficient Image-to-Image Translation
Yuxi Ren, Jie Wu, Peng Zhang, Manlin Zhang, Xuefeng Xiao, Qian He, Rui Wang, Min Zheng, Xin Pan
Generative Adversarial Network GAN Model Image to Image Translation State of the Art GAN GAN Compression Efficient GAN

May 29, 2023

Generative Adversarial Networks based Skin Lesion Segmentation
Shubham Innani, Prasad Dutande, Ujjwal Baid, Venu Pokuri, Spyridon Bakas, Sanjay Talbar, Bhakti Baheti, Sharath Chandra Guntuku
Generative Adversarial Network Lesion Segmentation Skin Lesion Segmentation Unsupervised Generative Lesion Aware Efficient GAN

February 28, 2023

DEff-GAN: Diverse Attribute Transfer for Few-Shot Image Synthesis
Rajiv Kumar, G. Sivakumar
GAN Model Image Synthesis C Gan Generalizable Feature Single GAN Efficient GAN

December 20, 2022

GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator
Jian Yang, Shuming Ma, Li Dong, Shaohan Huang, Haoyang Huang, Yuwei Yin, Dongdong Zhang, Liqun Yang, Furu Wei, Zhoujun Li
Generative Adversarial Network Pre Trained Language Model Encoder Decoder Encoder DEcoder Efficient GAN Auxiliary Encoder

July 4, 2022

Memory Efficient Patch-based Training for INR-based GANs
Namwoo Lee, Hyunsu Kim, Gayoung Lee, Sungjoo Yoo, Yunjey Choi
Training Data GAN Model Implicit Neural Representation Patch Based Memory Efficiency Efficient GAN

June 29, 2022

Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs
Bo-Kyeong Kim, Shinkook Choi, Hancheol Park
Generative Model Pruning Method Cut and Approximate Conditional GANs Talking Face Generation Efficient GAN