Corpus ID: 234778329

Fast Bayesian Uncertainty Estimation and Reduction of Batch Normalized Single Image Super-Resolution Network

@inproceedings{Kar2021FastBU,
  title={Fast Bayesian Uncertainty Estimation and Reduction of Batch Normalized Single Image Super-Resolution Network},
  author={Aupendu Kar and Prabir Kumar Biswas},
  booktitle={CVPR},
  year={2021}
}
Convolutional neural network (CNN) has achieved unprecedented success in image super-resolution tasks in recent years. However, the network’s performance depends on the distribution of the training sets and degrades on outof-distribution samples. This paper adopts a Bayesian approach for estimating uncertainty associated with output and applies it in a deep image super-resolution model to address the concern mentioned above. We use the uncertainty estimation technique using the batch… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 29 REFERENCES
Modelling uncertainty in deep learning for camera relocalization
  • Alex Kendall, R. Cipolla
  • Computer Science
  • 2016 IEEE International Conference on Robotics and Automation (ICRA)
  • 2016
TLDR
A Bayesian convolutional neural network is used to regress the 6-DOF camera pose from a single RGB image and an estimate of the model's relocalization uncertainty is obtained to improve state of the art localization accuracy on a large scale outdoor dataset. Expand
Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
TLDR
It is shown that training a deep network using batch normalization is equivalent to approximate inference in Bayesian models, and it is demonstrated how this finding allows us to make useful estimates of the model uncertainty. Expand
Densely Residual Laplacian Super-Resolution
  • Saeed Anwar, N. Barnes
  • Engineering, Computer Science
  • IEEE transactions on pattern analysis and machine intelligence
  • 2020
TLDR
This work presents a compact and accurate super-resolution algorithm, namely, Densely Residual Laplacian Network (DRLN), which employs cascading residual on the residual structure to allow the flow of low-frequency information to focus on learning high and mid-level features. Expand
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
TLDR
This work proposes a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long skip connections, and proposes a channel attention mechanism to adaptively rescale channel-wise features by considering interdependencies among channels. Expand
Residual Dense Network for Image Super-Resolution
TLDR
This paper proposes residual dense block (RDB) to extract abundant local features via dense connected convolutional layers and uses global feature fusion in RDB to jointly and adaptively learn global hierarchical features in a holistic way. Expand
Deep Learning for Image Super-Resolution: A Survey
TLDR
A survey on recent advances of image super-resolution techniques using deep learning approaches in a systematic way, which can roughly group the existing studies of SR techniques into three major categories: supervised SR, unsupervised SR, and domain-specific SR. Expand
Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
TLDR
A practical system which is able to predict pixel-wise class labels with a measure of model uncertainty, and shows that modelling uncertainty improves segmentation performance by 2-3% across a number of state of the art architectures such as SegNet, FCN and Dilation Network, with no additional parametrisation. Expand
Deep Back-Projection Networks for Super-Resolution
TLDR
It is shown that extending the idea to allow concatenation of features across up- and downsampling stages (Dense DBPN) allows us to reconstruct further improve super-resolution, yielding superior results and in particular establishing new state of the art results for large scaling factors such as 8× across multiple data sets. Expand
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. Expand
Second-Order Attention Network for Single Image Super-Resolution
TLDR
Experimental results demonstrate the superiority of the SAN network over state-of-the-art SISR methods in terms of both quantitative metrics and visual quality. Expand
...
1
2
3
...