ART-SS: An Adaptive Rejection Technique for Semi-Supervised restoration for adverse weather-affected images

TL;DR

This paper introduces ART-SS, an adaptive rejection technique that improves semi-supervised weather image restoration by filtering out unlabeled data that negatively impacts performance, demonstrated through extensive experiments.

Contribution

The paper presents a novel theoretical analysis and a practical sample rejection method that enhances semi-supervised weather image restoration performance.

Findings

Sample rejection improves deraining and dehazing results

The method significantly increases performance of existing SSR techniques

Theoretical insights guide effective unlabeled data filtering

Abstract

In recent years, convolutional neural network-based single image adverse weather removal methods have achieved significant performance improvements on many benchmark datasets. However, these methods require large amounts of clean-weather degraded image pairs for training, which is often difficult to obtain in practice. Although various weather degradation synthesis methods exist in the literature, the use of synthetically generated weather degraded images often results in sub-optimal performance on the real weather degraded images due to the domain gap between synthetic and real-world images. To deal with this problem, various semi-supervised restoration (SSR) methods have been proposed for deraining or dehazing which learn to restore the clean image using synthetically generated datasets while generalizing better using unlabeled real-world images. The performance of a semi-supervised method is essentially based on the quality of the unlabeled data. In particular, if the unlabeled data characteristics are very different from that of the labeled data, then the performance of a semi-supervised method degrades significantly. We theoretically study the effect of unlabeled data on the performance of an SSR method and develop a technique that rejects the unlabeled images that degrade the performance. Extensive experiments and ablation study show that the proposed sample rejection method increases the performance of existing SSR deraining and dehazing methods significantly. Code is available at :https://github.com/rajeevyasarla/ART-SS