Lipschitz Regularized CycleGAN for Improving Semantic Robustness in Unpaired Image-to-image Translation

9 Dec 2020 • Zhiwei Jia • Bodi Yuan • Kangkang Wang • Hong Wu • David Clifford • Zhiqiang Yuan • Hao Su

For unpaired image-to-image translation tasks, GAN-based approaches are susceptible to semantic flipping, i.e., contents are not preserved consistently. We argue that this is due to (1) the difference in semantic statistics between source and target domains and (2) the learned generators being non-robust... (read more)

PDF Abstract

Results from the Paper

Edit

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

METHOD	TYPE
Batch Normalization	Normalization
Residual Connection	Skip Connections
Sigmoid Activation	Activation Functions
Residual Block	Skip Connection Blocks
Convolution	Convolutions
PatchGAN	Discriminators
Tanh Activation	Activation Functions
Leaky ReLU	Activation Functions
Cycle Consistency Loss	Loss Functions
ReLU	Activation Functions
Instance Normalization	Normalization
GAN Least Squares Loss	Loss Functions
CycleGAN	Generative Models

METHOD

TYPE

Batch Normalization