• Corpus ID: 219898956

GDCA: GAN-based single image super resolution with Dual discriminators and Channel Attention

@article{Nguyen2021GDCAGS,
  title={GDCA: GAN-based single image super resolution with Dual discriminators and Channel Attention},
  author={Thanh-Khoa Nguyen and Hieu Trung Hoang and Chang-Dong Yoo},
  journal={ArXiv},
  year={2021},
  volume={abs/2111.05014}
}
Single Image Super Resolution (SISR) is a very active research field. This paper addresses SISR by using GAN-based approach with dual discriminators and incorporate with attention mechanism. The experimental results show that GDCA can generate sharper and high pleasing images compare to other conventional methods. Keywords— Deep Learning, Machine Learning, GAN, Attention 

Figures and Tables from this paper

References

SHOWING 1-8 OF 8 REFERENCES

Learning a Deep Convolutional Network for Image Super-Resolution

TLDR
This work proposes a deep learning method for single image super-resolution (SR) that directly learns an end-to-end mapping between the low/high-resolution images and shows that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.

Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

TLDR
This paper presents the first convolutional neural network capable of real-time SR of 1080p videos on a single K2 GPU and introduces an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output.

Accurate Image Super-Resolution Using Very Deep Convolutional Networks

TLDR
This work presents a highly accurate single-image superresolution (SR) method using a very deep convolutional network inspired by VGG-net used for ImageNet classification and uses extremely high learning rates enabled by adjustable gradient clipping.

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

TLDR
SRGAN, a generative adversarial network (GAN) for image super-resolution (SR), is presented, to its knowledge, the first framework capable of inferring photo-realistic natural images for 4x upscaling factors and a perceptual loss function which consists of an adversarial loss and a content loss.

Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model*

TLDR
Performance of existing model-free RL methods such as Soft Actor-Critic built on top of CCFDM outperforms prior state-of-the-art pixel-based RL methods on the DeepMind Control Suite benchmark.

Robust Maml: Prioritization Task Buffer with Adaptive Learning Process for Model-Agnostic Meta-Learning

TLDR
This paper proposes a more robust MAML based on an adaptive learning scheme and a prioritization task buffer referred to as Robust M AML (RMAML) for improving scalability of training process and alleviating the problem of distribution mismatch.

SRFeat: Single Image Super-Resolution with Feature Discrimination

TLDR
A novel GAN-based SISR method that overcomes the limitation and produces more realistic results by attaching an additional discriminator that works in the feature domain and design a new generator that utilizes long-range skip connections so that information between distant layers can be transferred more effectively.

A pre-training framework for learning feature representation in visual observation reinforcement learning

  • Conference of IEIE,
  • 2021