TY - GEN
T1 - Pix2Pix Hyperparameter Optimisation Towards Ideal Universal Image Quality Index Score
AU - Hölscher, Dirk
AU - Reich, Christoph
AU - Knahl, Martin
AU - Gut, Frank
AU - Clarke, Nathan
N1 - Publisher Copyright:
© 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2024
Y1 - 2024
N2 - Generative models and their possible applications are almost limitless. But there are still problems that such models have. On one hand, the models are difficult to train. Stability in training, mode collapse or non convergence, together with the huge parameter space make it extremely costly and difficult to train and optimize generative models. The following paper proposes an optimization method limited to a few hyperparameters with grid-search and early stopping which selects the best hyperparameter combination based on the results obtained with the Universal Image Quality Index (UIQ) by creating a copy of the source image and comparing it with the generated target. The proposed method allows to directly measure the impact of hyperparameter tuning by comparing the achieved UIQ score against a baseline.
AB - Generative models and their possible applications are almost limitless. But there are still problems that such models have. On one hand, the models are difficult to train. Stability in training, mode collapse or non convergence, together with the huge parameter space make it extremely costly and difficult to train and optimize generative models. The following paper proposes an optimization method limited to a few hyperparameters with grid-search and early stopping which selects the best hyperparameter combination based on the results obtained with the Universal Image Quality Index (UIQ) by creating a copy of the source image and comparing it with the generated target. The proposed method allows to directly measure the impact of hyperparameter tuning by comparing the achieved UIQ score against a baseline.
KW - Generative models
KW - Hyperparameter tuning
KW - Pix2Pix
KW - Quality assessment
KW - Universal image quality index
UR - http://www.scopus.com/inward/record.url?scp=85182504795&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-47721-8_57
DO - 10.1007/978-3-031-47721-8_57
M3 - Conference proceedings published in a book
AN - SCOPUS:85182504795
SN - 9783031477201
T3 - Lecture Notes in Networks and Systems
SP - 862
EP - 882
BT - Intelligent Systems and Applications - Proceedings of the 2023 Intelligent Systems Conference IntelliSys Volume 1
A2 - Arai, Kohei
PB - Springer Science and Business Media Deutschland GmbH
T2 - Intelligent Systems Conference, IntelliSys 2023
Y2 - 7 September 2023 through 8 September 2023
ER -