Adaptive Dropout: Unleashing Dropout across Layers for Generalizable Image Super-Resolution

TL;DR

This paper introduces Adaptive Dropout, a novel regularization technique for blind super-resolution that applies dropout across layers to improve generalization and reduce overfitting, outperforming previous methods.

Contribution

The paper proposes Adaptive Dropout, a new method that adaptively regularizes features at all network layers, addressing training-testing and layer-wise inconsistency issues in blind SR.

Findings

Outperforms previous regularization methods on benchmark datasets

Effective in synthetic and real-world image restoration tasks

Enhances generalization and reduces overfitting in blind SR

Abstract

Blind Super-Resolution (blind SR) aims to enhance the model's generalization ability with unknown degradation, yet it still encounters severe overfitting issues. Some previous methods inspired by dropout, which enhances generalization by regularizing features, have shown promising results in blind SR. Nevertheless, these methods focus solely on regularizing features before the final layer and overlook the need for generalization in features at intermediate layers. Without explicit regularization of features at intermediate layers, the blind SR network struggles to obtain well-generalized feature representations. However, the key challenge is that directly applying dropout to intermediate layers leads to a significant performance drop, which we attribute to the inconsistency in training-testing and across layers it introduced. Therefore, we propose Adaptive Dropout, a new regularization method for blind SR models, which mitigates the inconsistency and facilitates application across intermediate layers of networks. Specifically, for training-testing inconsistency, we re-design the form of dropout and integrate the features before and after dropout adaptively. For inconsistency in generalization requirements across different layers, we innovatively design an adaptive training strategy to strengthen feature propagation by layer-wise annealing. Experimental results show that our method outperforms all past regularization methods on both synthetic and real-world benchmark datasets, also highly effective in other image restoration tasks. Code is available at \href{https://github.com/xuhang07/Adpative-Dropout}{https://github.com/xuhang07/Adpative-Dropout}.