CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection

In this paper, we propose a novel CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection. Recent rapid advances in image manipulation tools and deep image synthesis techniques, such as Generative Adversarial Networks (GANs) have easily generated fake images, so detecting manipulated images has become an urgent issue... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


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

Methods used in the Paper


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