Investigating the Potential of Auxiliary-Classifier GANs for Image Classification in Low Data Regimes

01/22/2022
by   Amil Dravid, et al.
0

Generative Adversarial Networks (GANs) have shown promise in augmenting datasets and boosting convolutional neural networks' (CNN) performance on image classification tasks. But they introduce more hyperparameters to tune as well as the need for additional time and computational power to train supplementary to the CNN. In this work, we examine the potential for Auxiliary-Classifier GANs (AC-GANs) as a 'one-stop-shop' architecture for image classification, particularly in low data regimes. Additionally, we explore modifications to the typical AC-GAN framework, changing the generator's latent space sampling scheme and employing a Wasserstein loss with gradient penalty to stabilize the simultaneous training of image synthesis and classification. Through experiments on images of varying resolutions and complexity, we demonstrate that AC-GANs show promise in image classification, achieving competitive performance with standard CNNs. These methods can be employed as an 'all-in-one' framework with particular utility in the absence of large amounts of training data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/01/2019

GANchors: Realistic Image Perturbation Distributions for Anchors Using Generative Models

We extend and improve the work of Model Agnostic Anchors for explanation...
research
03/03/2021

Vanishing Twin GAN: How training a weak Generative Adversarial Network can improve semi-supervised image classification

Generative Adversarial Networks can learn the mapping of random noise to...
research
08/26/2019

End-to-End Conditional GAN-based Architectures for Image Colourisation

In this work recent advances in conditional adversarial networks are inv...
research
04/12/2021

Diamond in the rough: Improving image realism by traversing the GAN latent space

In just a few years, the photo-realism of images synthesized by Generati...
research
11/25/2020

Multiclass non-Adversarial Image Synthesis, with Application to Classification from Very Small Sample

The generation of synthetic images is currently being dominated by Gener...
research
10/27/2021

Fuzzy Generative Adversarial Networks

Generative Adversarial Networks (GANs) are well-known tools for data gen...

Please sign up or login with your details

Forgot password? Click here to reset