An improved generative network model for tackling mode collapse in medical leaf image generation

Article type: Research Article

Authors: Srilakshmi, A.^{; *} | Geetha, K.

Affiliations: School of Computing, Sastra Deemed to be University, Thanjavur, Thirumalaisamudram

Correspondence: [*] Corresponding author. A. Srilakshmi, Department of Computer Science, Sastra Deemed to be University, Thanjavur, Thirumalaisamudram. E-mail: srilakshmi.dreams@gmail.com.

Abstract: In this study, a unique generative adversarial network (GAN) architectural variation was suggested, which engages in adversarial game serve by preserving an appropriate distance in the latent dimension of the network. This method overcomes the mode collapse problem with a small dataset. Extensive experiments are conducted using the segmented medical leaf dataset with various classes and the generator network is able to produce all the artificial image classes. This is accomplished by combining a unique training technique with a reasonably simple model design.

Keywords: Mode collapse, image generation, generative adversarial networks, leaf images

DOI: 10.3233/JIFS-230212

Journal: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 2, pp. 2223-2233, 2023