Diff-HOD: Diffusion Model for Object Detection in Hazy Weather Conditions

• Published in: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 6285 - 6289
• Main Authors: Li, Yizhan, Yu, Rongwei, Shi, Junjie, Wang, Lina
• Format: Conference Proceeding
• Language: English
• Published: IEEE 14.04.2024
• Subjects: Diffusion models; Image dehazing; Image restoration; Interference; Joint learning; Multitasking; Noise measurement; Noise reduction; Object detection; Signal processing
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP48485.2024.10446872

The presence of haze negatively affects the visibility of captured images, posing challenges for general object detection models. We observe that current techniques exhibit three limitations: 1) they typically view image restoration and object detection as separate tasks; 2) they disregard potential details in degraded images that benefit detection; and 3) they lack sufficient recognition ability under haze interference. To this end, we propose a novel Diffusion Model (Diff-HOD) for Object Detection in Hazy weather conditions. Diff-HOD is a multi-task joint learning paradigm that integrates low-level image restoration and high-level object detection. Specifically, to bridge restoration and detection, we present a lightweight restoration module that mitigates the impact of weather-specific information, guiding the shared image encoder to provide high-quality features. We further leverage the excellent modeling ability of diffusion models to enhance the detection capability in hazy conditions. Moreover, we introduce an IoU-aware attention module that utilizes IoU as spatial priors to strengthen relevant features. Extensive experiments demonstrate that our Diff-HOD performs favorably against representative state-of-the-art approaches on both synthetic and natural datasets.