Pretraga

Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1113542

Evaluation of Generative Adversarial Network for Human Face Image Synthesis

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 ; Šarić, Matko (ur.).
Split: Fakultet elektrotehnike, strojarstva i brodogradnje Sveučilišta u Splitu, 2020. str. 89-95 doi:10.23919/SoftCOM50211.2020.9238203 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)

CROSBI ID: 1113542 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Evaluation of Generative Adversarial Network for Human Face Image Synthesis

Autori
Marin, Ivana ; Gotovac, Sven ; Russo, Mladen

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
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, 2020, 89-95

ISBN
978-953-290-099-6

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

Mjesto i datum
Hvar, Hrvatska; Split, Hrvatska, 17.09.2020. - 19.09.2020

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

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

Sažetak
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.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA

Ustanove:
Fakultet elektrotehnike, strojarstva i brodogradnje, Split,
Prirodoslovno-matematički fakultet, Split,
Sveučilište u Splitu

Profili:

Avatar Url Mladen Russo (autor)

Avatar Url Sven Gotovac (autor)

Avatar Url Ivana Marin (autor)

Poveznice na cjeloviti tekst rada:

doi ieeexplore.ieee.org ieeexplore.ieee.org

Citiraj ovu publikaciju:

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 ; Šarić, Matko (ur.).
Split: Fakultet elektrotehnike, strojarstva i brodogradnje Sveučilišta u Splitu, 2020. str. 89-95 doi:10.23919/SoftCOM50211.2020.9238203 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Marin, I., Gotovac, S. & Russo, M. (2020) Evaluation of Generative Adversarial Network for Human Face Image Synthesis. U: Begušić, D., Rožić, N., Radić, J. & Šarić, M. (ur.)SoftCOM 2020: 28th International Conference on Software, Telecommunications and Computer Networks: Virtual Conference: Proceedings doi:10.23919/SoftCOM50211.2020.9238203.
@article{article, author = {Marin, Ivana and Gotovac, Sven and Russo, Mladen}, year = {2020}, pages = {89-95}, DOI = {10.23919/SoftCOM50211.2020.9238203}, keywords = {Evaluation, Fr\'{e}chet Inception Distance, Generative Adversarial Networks, Inception Score, Latent Space Exploration}, doi = {10.23919/SoftCOM50211.2020.9238203}, isbn = {978-953-290-099-6}, title = {Evaluation of Generative Adversarial Network for Human Face Image Synthesis}, keyword = {Evaluation, Fr\'{e}chet Inception Distance, Generative Adversarial Networks, Inception Score, Latent Space Exploration}, publisher = {Fakultet elektrotehnike, strojarstva i brodogradnje Sveu\v{c}ili\v{s}ta u Splitu}, publisherplace = {Hvar, Hrvatska; Split, Hrvatska} }
@article{article, author = {Marin, Ivana and Gotovac, Sven and Russo, Mladen}, year = {2020}, pages = {89-95}, DOI = {10.23919/SoftCOM50211.2020.9238203}, keywords = {Evaluation, Fr\'{e}chet Inception Distance, Generative Adversarial Networks, Inception Score, Latent Space Exploration}, doi = {10.23919/SoftCOM50211.2020.9238203}, isbn = {978-953-290-099-6}, title = {Evaluation of Generative Adversarial Network for Human Face Image Synthesis}, keyword = {Evaluation, Fr\'{e}chet Inception Distance, Generative Adversarial Networks, Inception Score, Latent Space Exploration}, publisher = {Fakultet elektrotehnike, strojarstva i brodogradnje Sveu\v{c}ili\v{s}ta u Splitu}, publisherplace = {Hvar, Hrvatska; Split, Hrvatska} }

Časopis indeksira:


  • Scopus

Citati:

    Altmetrijski pokazatelji:


    Podijeli:





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font
    CROSBI koristi kolačiće (cookies) kako bi poboljšao funkcionalnost stranice.