DFE-RFC: Degradation-Robust Feature Network for Object Detection in Adverse Weather

Abstract

In recent years, object detection methods for adverse weather conditions have developed rapidly, alleviating to some extent the significant performance degradation of conventional object detection methods caused by image degradation. However, existing object detection methods still struggle to effectively represent weak target cues, such as edges, textures, and local structural information. These fragile features are further lost during downsampling, thereby limiting detection performance. To address this issue, we propose DFE-RFC, which enhances feature representation and information preservation under complex degradations through the joint introduction of degradation feature enhancement and robust feature compression. Specifically, we design a Degradation Feature Enhancement (DFE) module, which incorporates a degradation response map and a residual modulation mechanism into a channel and spatial attention framework, thereby enhancing the network’s ability to represent target edges, textures, and local structures in degraded scenes. In addition, we propose a Robust Feature Compression (RFC) method, which introduces an auxiliary pooling branch during downsampling to compensate the compressed output of the main branch with structural information, thereby preserving key discriminative information and reducing the loss of fine details caused by spatial compression. Experimental results on the DAWN adverse weather dataset demonstrate that the proposed DFE-RFC method achieves promising detection performance and verify the effectiveness of the proposed method.