Geometry-preserving losses based on tangent-space distances improve blackbox GAN adaptation to shifted distributions compared with standard losses.
Available: https://arxiv.org/abs/2002.10964
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Fully hybrid quantum-classical GANs with VQCs in both generator and discriminator outperform classical baselines in image quality and metrics, with placement effects on convergence and sustained performance on reduced datasets.
citing papers explorer
-
Geometry Preserving Loss Functions Promote Improved Adaptation of Blackbox Generative Model
Geometry-preserving losses based on tangent-space distances improve blackbox GAN adaptation to shifted distributions compared with standard losses.
-
Hybrid Quantum-Classical Generative Adversarial Networks with Transfer Learning
Fully hybrid quantum-classical GANs with VQCs in both generator and discriminator outperform classical baselines in image quality and metrics, with placement effects on convergence and sustained performance on reduced datasets.