Self-Attention Generative Adversarial Networks
Explore this paper's citation graph
Summary
The proposed SAGAN achieves the state-of-the-art results, boosting the best published Inception score from 36.8 to 52.52 and reducing Frechet Inception distance from 27.62 to 18.65 on the challenging ImageNet dataset.
- Type
- preprint
- Published
- 2018-05-21
- Cited by
- 4,180
- References
- 54
- Access
- Open access
- OpenAlex
- https://openalex.org/W2804078698
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:46898260
Keywords
Discriminator, Boosting (machine learning), Computer science, Normalization (sociology), Generative grammar
References
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- ImageNet Large Scale Visual Recognition Challenge
- Long Short-Term Memory-Networks for Machine Reading
- Faster Asynchronous SGD
- Generative Adversarial Text to Image Synthesis
- A Decomposable Attention Model for Natural Language Inference
- Improved Techniques for Training GANs
- Coupled Generative Adversarial Networks
- Learning What and Where to Draw
- Image-to-Image Translation with Conditional Adversarial Networks
- Unrolled Generative Adversarial Networks
- StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks
- Deep and Hierarchical Implicit Models
- SegAN: Adversarial Network with Multi-scale L1 Loss for Medical Image Segmentation
- StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
- PixelSNAIL: An Improved Autoregressive Generative Model
- Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis
- The relativistic discriminator: a key element missing from standard GAN
- Skill Rating for Generative Models
- Discriminator Rejection Sampling
Cited by
- Generative-Discriminative Complementary Learning
- Targeted Kernel Networks: Faster Convolutions with Attentive Regularization
- A New Framework for Machine Intelligence: Concepts and Prototype
- Generative Reversible Networks
- Unsupervised Attention-guided Image to Image Translation
- GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
- Ambient Hidden Space of Generative Adversarial Networks
- The GAN Landscape: Losses, Architectures, Regularization, and Normalization
- Training Generative Reversible Networks
- Inverse molecular design using machine learning: Generative models for matter engineering
- Multi-Perspective Neural Architecture for Recommendation System
- Language Guided Fashion Image Manipulation with Feature-wise Transformations
- Self-attention recurrent network for saliency detection
- A Review of Learning with Deep Generative Models from perspective of graphical modeling
- Rethinking Monocular Depth Estimation with Adversarial Training
- Whispered-to-voiced Alaryngeal Speech Conversion with Generative Adversarial Networks
- Crowd-Robot Interaction: Crowd-Aware Robot Navigation With Attention-Based Deep Reinforcement Learning
- Close to Human Quality TTS with Transformer
- Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts
- Understanding the Effectiveness of Lipschitz-Continuity in Generative Adversarial Nets
Related papers
- Discriminator-Quality Evaluation GAN
- A high-performance, low-cost, leading edge discriminator
- Analysis and computer simulation of a delay discriminator
- Design and Implementation of the Discriminator with Half Approximation Structure in Code Tracking Loop for GPS
- Dynamically Masked Discriminator for Generative Adversarial Networks
- Private GANs, Revisited
- A Gaussian quantum state discriminator
- Bridging adversarial samples and adversarial networks
- Improved Boundary Equilibrium Generative Adversarial Networks