SETGAN: Scale and Energy Trade-off GANs for Image Applications on Mobile Platforms
Not on the map. Why?
Abstract (arXiv)
We consider the task of photo-realistic unconditional image generation (generate high quality, diverse samples that carry the same visual content as the image) on mobile platforms using Generative Adversarial Networks (GANs). In this paper, we propose a novel approach to trade-off image generation accuracy of a GAN for the energy consumed (compute) at run-time called Scale-Energy Tradeoff GAN (SETGAN). GANs usually take a long time to train and consume a huge memory hence making it difficult to run on edge devices. The key idea behind SETGAN for an image generation task is for a given input image, we train a GAN on a remote server and use the trained model on edge devices. We use SinGAN, a single image unconditional generative model, that contains a pyramid of fully convolutional GANs, each responsible for learning the patch distribution at a different scale of the image. During the training process, we determine the optimal number of scales for a given input image and the energy constraint from the target edge device. Results show that with SETGAN's unique client-server-based architecture, we were able to achieve a 56% gain in energy for a loss of 3% to 12% SSIM accuracy. Also, with the parallel multi-scale training, we obtain around 4x gain in training time on the server.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 19 of its 41 references that are in the map. First posted on arXiv 23 Mar 2021.
Builds on
19 of 41 references.
References · 19
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
- 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
- 2019SinGAN: Learning a Generative Model from a Single Natural Imagecited by 348
- 2016EIE: Efficient Inference Engine on Compressed Deep Neural Networkcited by 291
- 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 285
- 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 133
- 2020Max-value Entropy Search for Multi-Objective Bayesian Optimization with Constraintscited by 81
- 2015Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognitioncited by 67
7 more
- 2017Learning Texture Manifolds with the Periodic Spatial GANcited by 53
- 2017TextureGAN: Controlling Deep Image Synthesis with Texture Patchescited by 47
- 2016Texture Synthesis with Spatial Generative Adversarial Networkscited by 45
- 2018Designing Adaptive Neural Networks for Energy-Constrained Image Classificationcited by 18
- 2016Saliency Driven Image Manipulationcited by 9
- 2019Trading-off Accuracy and Energy of Deep Inference on Embedded Systems: A Co-Design Approachcited by 8
- 2020An Energy-Aware Online Learning Framework for Resource Management in Heterogeneous Platformscited by 3
Built on by
Citing papers per year: 2021: 1.
1 paper.