Corpus ID: 46898260

Self-Attention Generative Adversarial Networks

@inproceedings{Zhang2019SelfAttentionGA,
  title={Self-Attention Generative Adversarial Networks},
  author={Han Zhang and Ian J. Goodfellow and Dimitris N. Metaxas and Augustus Odena},
  booktitle={ICML},
  year={2019}
}
In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks. [...] Key Method Moreover, the discriminator can check that highly detailed features in distant portions of the image are consistent with each other. Furthermore, recent work has shown that generator conditioning affects GAN performance.Expand
Dual Contrastive Loss and Attention for GANs
TLDR
A novel dual contrastive loss is proposed and it is shown that, with this loss, discriminator learns more generalized and distinguishable representations to incentivize generation to further push the boundaries in image generation. Expand
Multi-Attention Generative Adversarial Network for image captioning
TLDR
A Multi-Attention mechanism is first proposed by utilizing both of the local and non-local evidence for more effective feature representation and reasoning in image captioning. Expand
Attentive Semantic and Perceptual Faces Completion Using Self-attention Generative Adversarial Networks
  • Xiaowei Liu, Kenli Li, Keqin Li
  • Computer Science
  • Neural Processing Letters
  • 2019
TLDR
An approach based on self-attention generative adversarial networks to accomplish the task of image completion where completed images become globally and locally consistent and attentive recurrent neural block is introduced to obtain the attention map about the missing part in the image. Expand
Generative adversarial networks: a survey on applications and challenges
TLDR
The nuts and bolts of GANs, state-of-the-art related work and its applications, evaluation metrics, challenges involved in training GAns, and benchmark datasets that would benefit naive and enthusiastic researchers who are interested in working on GANS are presented. Expand
Attention-Guided Generative Adversarial Networks for Unsupervised Image-to-Image Translation
TLDR
This paper proposes a novel Attention-Guided Generative Adversarial Network (AGGAN), which can detect the most discriminative semantic object and minimize changes of unwanted part for semantic manipulation problems without using extra data and models. Expand
Improved Transformer for High-Resolution GANs
TLDR
The proposed HiT is an important milestone for generators in GANs which are completely free of convolutions and has a linear computational complexity with respect to the image size and thus directly scales to synthesizing high definition images. Expand
Dairy Goat Image Generation Based on Improved-Self-Attention Generative Adversarial Networks
TLDR
An improved-self-attention GANs (Improved-SAGAN) is put forward to improve the method for calculating correlation in the SAGAN to better measure the correlation between features by normalizing the feature vectors to eliminate as many errors caused by noise as possible. Expand
Auto-Embedding Generative Adversarial Networks For High Resolution Image Synthesis
TLDR
A novel GAN is developed called auto-embedding generative adversarial network, which simultaneously encodes the global structure features and captures the fine-grained details of real images, and is able to produce high-resolution images of promising quality directly from the input noise. Expand
Dualattn-GAN: Text to Image Synthesis With Dual Attentional Generative Adversarial Network
TLDR
A Dual Attentional Generative Adversarial Network (DualAttn-GAN) is proposed in which the dual attention modules are introduced to enhance local details and global structures by attending to related features from relevant words and different visual regions. Expand
Linear Semantics in Generative Adversarial Networks
  • Jianjin Xu, Changxi Zheng
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021
TLDR
This work aims to better understand the semantic representation of GANs, and thereby enable semantic control in GAN’s generation process, and finds that a well-trained GAN encodes image semantics in its internal feature maps in a surprisingly simple way. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 57 REFERENCES
AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
TLDR
An Attentional Generative Adversarial Network that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation and for the first time shows that the layered attentional GAN is able to automatically select the condition at the word level for generating different parts of the image. Expand
A Style-Based Generator Architecture for Generative Adversarial Networks
TLDR
An alternative generator architecture for generative adversarial networks is proposed, borrowing from style transfer literature, that improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation. Expand
Energy-based Generative Adversarial Network
We introduce the "Energy-based Generative Adversarial Network" model (EBGAN) which views the discriminator as an energy function that attributes low energies to the regions near the data manifold andExpand
Improved Techniques for Training GANs
TLDR
This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes. Expand
Learning What and Where to Draw
TLDR
This work proposes a new model, the Generative Adversarial What-Where Network (GAWWN), that synthesizes images given instructions describing what content to draw in which location, and shows high-quality 128 x 128 image synthesis on the Caltech-UCSD Birds dataset. Expand
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
TLDR
Extensive experiments demonstrate that the proposed stacked generative adversarial networks significantly outperform other state-of-the-art methods in generating photo-realistic images. Expand
Large Scale GAN Training for High Fidelity Natural Image Synthesis
TLDR
It is found that applying orthogonal regularization to the generator renders it amenable to a simple "truncation trick," allowing fine control over the trade-off between sample fidelity and variety by reducing the variance of the Generator's input. Expand
Image Transformer
TLDR
This work generalizes a recently proposed model architecture based on self-attention, the Transformer, to a sequence modeling formulation of image generation with a tractable likelihood, and significantly increases the size of images the model can process in practice, despite maintaining significantly larger receptive fields per layer than typical convolutional neural networks. Expand
Improved Training of Wasserstein GANs
TLDR
This work proposes an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input, which performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning. Expand
...
1
2
3
4
5
...