# Test-time Adaptation for Real Image Denoising via Meta-transfer Learning

arXiv: https://arxiv.org/abs/2207.02066 · HTML: https://mlsanity.com/paper/2207.02066/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 29 references that are in the map.
- First posted on arXiv 5 Jul 2022.

## Builds on (most cited first, 22 of 22)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising](https://mlsanity.com/paper/1710.04026/) (2017)
- [Learning Deep CNN Denoiser Prior for Image Restoration](https://mlsanity.com/paper/1704.03264/) (2017)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML](https://mlsanity.com/paper/1909.09157/) (2019)
- [Meta-Transfer Learning for Few-Shot Learning](https://mlsanity.com/paper/1812.02391/) (2018)
- [Residual Non-local Attention Networks for Image Restoration](https://mlsanity.com/paper/1903.10082/) (2019)
- [Residual Dense Network for Image Restoration](https://mlsanity.com/paper/1812.10477/) (2018)
- [Real Image Denoising with Feature Attention](https://mlsanity.com/paper/1904.07396/) (2019)
- [Non-Local Recurrent Network for Image Restoration](https://mlsanity.com/paper/1806.02919/) (2018)
- [Learning Enriched Features for Fast Image Restoration and Enhancement](https://mlsanity.com/paper/2205.01649/) (2022)
- [Densely Connected Pyramid Dehazing Network](https://mlsanity.com/paper/1803.08396/) (2018)
- [Meta-Transfer Learning for Zero-Shot Super-Resolution](https://mlsanity.com/paper/2002.12213/) (2020)
- [Self-Supervised Generalisation with Meta Auxiliary Learning](https://mlsanity.com/paper/1901.08933/) (2019)
- [Real-world Noisy Image Denoising: A New Benchmark](https://mlsanity.com/paper/1804.02603/) (2018)
- [When AWGN-based Denoiser Meets Real Noises](https://mlsanity.com/paper/1904.03485/) (2019)
- [GRDN:Grouped Residual Dense Network for Real Image Denoising and GAN-based Real-world Noise Modeling](https://mlsanity.com/paper/1905.11172/) (2019)
- [Designing and Training of A Dual CNN for Image Denoising](https://mlsanity.com/paper/2007.03951/) (2020)
- [Self-Supervised Fast Adaptation for Denoising via Meta-Learning](https://mlsanity.com/paper/2001.02899/) (2020)
- [CT Image Denoising with Perceptive Deep Neural Networks](https://mlsanity.com/paper/1702.07019/) (2017)

## Built on by (most cited first, 3 of 3)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [LAN: Learning to Adapt Noise for Image Denoising](https://mlsanity.com/paper/2412.10651/) (2024)
- [Test-time Adaptation Meets Image Enhancement: Improving Accuracy via Uncertainty-aware Logit Switching](https://mlsanity.com/paper/2403.17423/) (2024)

## Abstract (arXiv)

In recent years, a ton of research has been conducted on real image denoising tasks. However, the efforts are more focused on improving real image denoising through creating a better network architecture. We explore a different direction where we propose to improve real image denoising performance through a better learning strategy that can enable test-time adaptation on the multi-task network. The learning strategy is two stages where the first stage pre-train the network using meta-auxiliary learning to get better meta-initialization. Meanwhile, we use meta-learning for fine-tuning (meta-transfer learning) the network as the second stage of our training to enable test-time adaptation on real noisy images. To exploit a better learning strategy, we also propose a network architecture with self-supervised masked reconstruction loss. Experiments on a real noisy dataset show the contribution of the proposed method and show that the proposed method can outperform other SOTA methods.