Nalazite se na CroRIS probnoj okolini. Ovdje evidentirani podaci neće biti pohranjeni u Informacijskom sustavu znanosti RH. Ako je ovo greška, CroRIS produkcijskoj okolini moguće je pristupi putem poveznice www.croris.hr
izvor podataka: crosbi

Evaluation of Generative Adversarial Network for Human Face Image Synthesis (CROSBI ID 700289)

Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija

Marin, Ivana ; Gotovac, Sven ; Russo, Mladen Evaluation of Generative Adversarial Network for Human Face Image Synthesis // SoftCOM 2020: 28th International Conference on Software, Telecommunications and Computer Networks: Virtual Conference: Proceedings / Begušić, Dinko ; Rožić, Nikola ; Radić, Joško et al. (ur.). Split: Fakultet elektrotehnike, strojarstva i brodogradnje Sveučilišta u Splitu, 2020. str. 89-95 doi: 10.23919/SoftCOM50211.2020.9238203

Podaci o odgovornosti

Marin, Ivana ; Gotovac, Sven ; Russo, Mladen

engleski

Evaluation of Generative Adversarial Network for Human Face Image Synthesis

Meaningful and objective evaluation metric for fair model comparison is crucial for further scientific progress in the field of deep generative modeling. Despite the significant progress and impressive results obtained by Generative Adversarial Networks in recent years, the problem of their objective evaluation remains open. In this paper, we give an overview of qualitative and quantitative evaluation measures most frequently used to assess the quality of generated images and learned representations of an adversarial network together with the empirical comparison of their performance on the problem of human face image synthesis. It is shown that evaluation scores of the two most widely accepted quantitative metrics, Inception Score (IS) and Fréchet Inception Distance (FID), do not correlate. The IS is not an appropriate evaluation metric for a given problem, but FID shows good performance that correlates well with a visual inspection of generated samples. The qualitative evaluation can be used to complement results obtained with quantitative evaluation - to gain further insight into the learned data representation and detect possible overfitting.

Evaluation ; Fréchet Inception Distance ; Generative Adversarial Networks ; Inception Score ; Latent Space Exploration

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

Podaci o prilogu

89-95.

2020.

objavljeno

10.23919/SoftCOM50211.2020.9238203

Podaci o matičnoj publikaciji

SoftCOM 2020: 28th International Conference on Software, Telecommunications and Computer Networks: Virtual Conference: Proceedings

Begušić, Dinko ; Rožić, Nikola ; Radić, Joško ; Šarić, Matko

Split: Fakultet elektrotehnike, strojarstva i brodogradnje Sveučilišta u Splitu

978-953-290-099-6

1847-358X

Podaci o skupu

28th International Conference on Software, Telecommunications and Computer Networks, SoftCOM 2020

predavanje

17.09.2020-19.09.2020

Hvar, Hrvatska; Split, Hrvatska

Povezanost rada

Računarstvo

Poveznice
Indeksiranost