CVJul 5, 2022

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

arXiv:2207.02066v14 citationsh-index: 9
Originality Incremental advance
AI Analysis

This addresses the problem of adapting denoising models to real-world noise during testing, offering an incremental improvement over existing methods.

The paper tackles real image denoising by proposing a two-stage meta-transfer learning strategy for test-time adaptation, which outperforms other state-of-the-art methods on a real noisy dataset.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes