Self-Attention GAN

Introduced by Zhang et al. in Self-Attention Generative Adversarial Networks

The Self-Attention Generative Adversarial Network, or SAGAN, allows for attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details as a function of only spatially local points in lower-resolution feature maps. In SAGAN, details can be generated using cues from all feature locations. Moreover, the discriminator can check that highly detailed features in distant portions of the image are consistent with each other.

Source: Self-Attention Generative Adversarial Networks

Read Paper See Code

Papers

Paper	Code	Results	Date	Stars

Tasks

Task	Papers	Share
Image Generation	40	18.96%
Conditional Image Generation	17	8.06%
Multi-agent Reinforcement Learning	7	3.32%
Super-Resolution	6	2.84%
Reinforcement Learning (RL)	6	2.84%
Image-to-Image Translation	6	2.84%
Translation	6	2.84%
Decision Making	5	2.37%
Denoising	4	1.90%

Usage Over Time

This feature is experimental; we are continuously improving our matching algorithm.

Components

Component	Type	Add Remove
Adam	Stochastic Optimization
Batch Normalization	Normalization
Convolution	Convolutions
GAN Hinge Loss	Loss Functions
SAGAN Self-Attention Module	Attention Modules
Spectral Normalization	Normalization

Categories

Add Remove

Generative Adversarial Networks