Detection-Friendly Dehazing: Object Detection in Real-World Hazy Scenes

Adverse weather conditions in real-world scenarios lead to performance degradation of deep learning-based detection models. A well-known method is to use image restoration methods to enhance degraded images before object detection. However, how to build a positive correlation between these two tasks is still technically challenging. The restoration labels are also unavailable in practice. To this end, taking the hazy scene as an example, we propose a union architecture BAD-Net that connects the dehazing module and detection module in an end-to-end manner. Specifically, we design a two-branch structure with an attention fusion module for fully combining hazy and dehazing features. This reduces bad impacts on the detection module when the dehazing module performs poorly. Besides, we introduce a self-supervised haze robust loss that enables the detection module to deal with different degrees of haze. Most importantly, an interval iterative data refinement training strategy is proposed to guide the dehazing module learning with weak supervision. BAD-Net improves further detection performance through detection-friendly dehazing. Extensive experiments on RTTS and VOChaze datasets show that BAD-Net achieves higher accuracy compared to the recent state-of-the-art methods. It is a robust detection framework for bridging the gap between low-level dehazing and high-level detection.

Automated summary

This article introduces a joint architecture BAD-Net that connects the dehazing module and detection module to improve the performance of deep learning-based object detection models. By designing a two-branch structure with an attention fusion module, hazy and dehazing features are fully combined, reducing the impact of poor performance in the dehazing module on the detection module. A self-supervised haze robust loss is introduced to enable the detection module to handle different degrees of haze. Additionally, an interval iterative data refinement training strategy is proposed to guide the learning process of the dehazing module. BAD-Net enhances detection performance through detection-friendly dehazing and achieves higher accuracy compared to state-of-the-art methods on RTTS and VOChaze datasets.