Adapting Triple-BigGAN for Image Detection Tasks: Challenges and Opportunities-Reference-Cited by-同舟云学术

Adapting Triple-BigGAN for Image Detection Tasks: Challenges and Opportunities

Published:2024-04-17 Issue: Volume: Page:
ISSN:
Container-title:
language:
Short-container-title:

Author:

Quaicoo Russell¹,Acheampong Richmond¹,Gyamenah Pius¹^ORCID,Dodoo Albert Ankomah¹^ORCID,Soli Michael Agbo Tettey¹^ORCID,Appati Justice Kwame¹^ORCID

Affiliation:

1. University of Ghana

Abstract

Abstract Recent years have seen notable progress in generative modeling, leading to the emergence of the Triple-BigGAN model as an extension of the pioneering BigGAN model. This thesis scrutinizes the Triple-BigGAN model, investigating its role in augmenting image quality and its integration with a co-trained classifier. Through comprehensive experimentation and analysis, this research probes into the complexities encountered during experimentation and the insights gleaned from employing varied computational environments such as Google Colab, Kaggle Notebooks, and Google Vertex AI. Utilizing metrics like Fréchet Inception Distance (FID), Inception Score (IS), categorical cross-entropy loss, and accuracy, the dissertation evaluates the algorithm's efficacy in both image generation and classification tasks. It delineates the delicate balance among the generator, discriminator, and classifier elements within the model. This exploration of the Triple-BigGAN algorithm contributes to a deeper comprehension of advanced generative models, elucidating their potentials and challenges while laying the groundwork for further advancements at the nexus of generative and discriminative AI techniques.

Publisher

Research Square Platform LLC

Reference23 articles.

1. Featurized bidirectional gan: Adversarial defense via adversarially learned semantic inference;Bao R;arXiv preprint arXiv,2018

2. Barreraa K, Merino A, Molina A, Rodellar J (2022) Automatic generation of artificial images of leukocytes and leukemic. Computer Methods and Programs in Biomedicine, p 16

3. Large scale GAN training for high fidelity natural image synthesis;Brock A;arXiv preprint arXiv,2018

4. Neural photo editing with introspective adversarial networks;Brock A;arXiv preprint arXiv,2016

5. Brownlee J (2021) Generative Adversarial Networks with Python: Deep Learning Generative Models for image synthesis and image translation. Jason Brownlee