Geometry-preserving losses based on tangent-space distances improve blackbox GAN adaptation to shifted distributions compared with standard losses.
In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2021)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.