SETGAN: Scale and Energy Trade-off GANs for Image Applications on Mobile Platforms

03/23/2021
by   Nitthilan Kannappan Jayakodi, et al.
0

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 for a loss of 3 training, we obtain around 4x gain in training time on the server.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

page 4

page 6

page 7

page 8

05/02/2019

SinGAN: Learning a Generative Model from a Single Natural Image

We introduce SinGAN, an unconditional generative model that can be learn...
09/29/2020

TinyGAN: Distilling BigGAN for Conditional Image Generation

Generative Adversarial Networks (GANs) have become a powerful approach f...
01/28/2018

Improved Training of Generative Adversarial Networks Using Representative Features

Despite of the success of Generative Adversarial Networks (GANs) for ima...
10/01/2020

Tabular GANs for uneven distribution

GANs are well known for success in the realistic image generation. Howev...
05/14/2019

Kernel Mean Matching for Content Addressability of GANs

We propose a novel procedure which adds "content-addressability" to any ...
09/17/2021

Diverse Generation from a Single Video Made Possible

Most advanced video generation and manipulation methods train on a large...
11/28/2020

Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs

While Generative Adversarial Networks (GANs) show increasing performance...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.