JDATT: A Joint Distillation Framework for Atmospheric Turbulence Mitigation and Target Detection

TL;DR

JDATT is a unified framework that combines atmospheric turbulence mitigation and target detection using knowledge distillation, achieving high performance with reduced complexity suitable for real-time applications.

Contribution

It introduces a joint distillation approach that integrates turbulence mitigation and detection, optimizing both tasks simultaneously in a lightweight model.

Findings

Outperforms existing methods in visual restoration and detection accuracy.

Reduces model size and inference time significantly.

Effective on both synthetic and real-world turbulence datasets.

Abstract

Atmospheric turbulence (AT) introduces severe degradations, such as rippling, blur, and intensity fluctuations, that hinder both image quality and downstream vision tasks like target detection. While recent deep learning-based approaches have advanced AT mitigation using transformer and Mamba architectures, their high complexity and computational cost make them unsuitable for real-time applications, especially in resource-constrained settings such as remote surveillance. Moreover, the common practice of separating turbulence mitigation and object detection leads to inefficiencies and suboptimal performance. To address these challenges, we propose JDATT, a Joint Distillation framework for Atmospheric Turbulence mitigation and Target detection. JDATT integrates state-of-the-art AT mitigation and detection modules and introduces a unified knowledge distillation strategy that compresses both components while minimizing performance loss. We employ a hybrid distillation scheme: feature-level distillation via Channel-Wise Distillation (CWD) and Masked Generative Distillation (MGD), and output-level distillation via Kullback-Leibler divergence. Experiments on synthetic and real-world turbulence datasets demonstrate that JDATT achieves superior visual restoration and detection accuracy while significantly reducing model size and inference time, making it well-suited for real-time deployment.