Towards Generalization on Real Domain for Single Image Dehazing via Meta-Learning

TL;DR

This paper introduces a domain generalization framework using meta-learning for single image dehazing that effectively captures domain-specific features without test-time training, improving performance on real-world hazy images.

Contribution

The proposed method employs adaptation and distance-aware aggregation networks with a novel contrastive regularization to enhance domain generalization in image dehazing.

Findings

Outperforms state-of-the-art methods on real hazy datasets

Effectively captures domain-specific features without test-time training

Demonstrates superior generalization ability in real-world scenarios

Abstract

Learning-based image dehazing methods are essential to assist autonomous systems in enhancing reliability. Due to the domain gap between synthetic and real domains, the internal information learned from synthesized images is usually sub-optimal in real domains, leading to severe performance drop of dehaizing models. Driven by the ability on exploring internal information from a few unseen-domain samples, meta-learning is commonly adopted to address this issue via test-time training, which is hyperparameter-sensitive and time-consuming. In contrast, we present a domain generalization framework based on meta-learning to dig out representative and discriminative internal properties of real hazy domains without test-time training. To obtain representative domain-specific information, we attach two entities termed adaptation network and distance-aware aggregator to our dehazing network. The adaptation network assists in distilling domain-relevant information from a few hazy samples and caching it into a collection of features. The distance-aware aggregator strives to summarize the generated features and filter out misleading information for more representative internal properties. To enhance the discrimination of distilled internal information, we present a novel loss function called domain-relevant contrastive regularization, which encourages the internal features generated from the same domain more similar and that from diverse domains more distinct. The generated representative and discriminative features are regarded as some external variables of our dehazing network to regress a particular and powerful function for a given domain. The extensive experiments on real hazy datasets, such as RTTS and URHI, validate that our proposed method has superior generalization ability than the state-of-the-art competitors.