# Deep Gaussian Denoiser Epistemic Uncertainty and Decoupled Dual-Attention Fusion

arXiv: https://arxiv.org/abs/2101.04631 · HTML: https://mlsanity.com/paper/2101.04631/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 12 Jan 2021.

## Builds on (most cited first, 12 of 12)

- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Attention on Attention for Image Captioning](https://mlsanity.com/paper/1908.06954/) (2019)
- [MemNet: A Persistent Memory Network for Image Restoration](https://mlsanity.com/paper/1708.02209/) (2017)
- [Real Image Denoising with Feature Attention](https://mlsanity.com/paper/1904.07396/) (2019)
- [Towards Robust Neural Networks via Random Self-ensemble](https://mlsanity.com/paper/1712.00673/) (2017)
- [Regularization by Denoising via Fixed-Point Projection (RED-PRO)](https://mlsanity.com/paper/2008.00226/) (2020)
- [When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach](https://mlsanity.com/paper/1706.04284/) (2017)
- [Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning](https://mlsanity.com/paper/1907.03029/) (2019)
- [End-to-end Flow Correlation Tracking with Spatial-temporal Attention](https://mlsanity.com/paper/1711.01124/) (2017)
- [Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks](https://mlsanity.com/paper/2003.07119/) (2020)
- [Collegial Ensembles](https://mlsanity.com/paper/2006.07678/) (2020)
- [Towards Boosting the Channel Attention in Real Image Denoising : Sub-band Pyramid Attention](https://mlsanity.com/paper/2012.12481/) (2020)

## Built on by (most cited first, 4 of 4)

- [PoGaIN: Poisson-Gaussian Image Noise Modeling from Paired Samples](https://mlsanity.com/paper/2210.04866/) (2022)
- [Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks](https://mlsanity.com/paper/2106.00673/) (2021)
- [Image Denoising with Control over Deep Network Hallucination](https://mlsanity.com/paper/2201.00429/) (2022)
- [Target Aware Poisson-Gaussian Noise Parameters Estimation from Noisy Images](https://mlsanity.com/paper/2210.12142/) (2022)

## Abstract (arXiv)

Following the performance breakthrough of denoising networks, improvements have come chiefly through novel architecture designs and increased depth. While novel denoising networks were designed for real images coming from different distributions, or for specific applications, comparatively small improvement was achieved on Gaussian denoising. The denoising solutions suffer from epistemic uncertainty that can limit further advancements. This uncertainty is traditionally mitigated through different ensemble approaches. However, such ensembles are prohibitively costly with deep networks, which are already large in size. Our work focuses on pushing the performance limits of state-of-the-art methods on Gaussian denoising. We propose a model-agnostic approach for reducing epistemic uncertainty while using only a single pretrained network. We achieve this by tapping into the epistemic uncertainty through augmented and frequency-manipulated images to obtain denoised images with varying error. We propose an ensemble method with two decoupled attention paths, over the pixel domain and over that of our different manipulations, to learn the final fusion. Our results significantly improve over the state-of-the-art baselines and across varying noise levels.