# CW-DETR: An Efficient Detection Transformer for Traffic Signs in Complex Weather

## TL;DR

This paper introduces CW-DETR, a new detection system that improves traffic sign recognition in bad weather like rain, fog, and snow.

## Contribution

The paper proposes CW-DETR with four novel modules to enhance traffic sign detection under complex weather conditions.

## Key findings

- CW-DETR achieves 69.0% AP and 94.4% AP50 on the CCTSDB2021 dataset, outperforming existing real-time detectors.
- The model maintains computational efficiency with 56.8 GFLOPs and shows robust generalization across multiple datasets and real-world snow conditions.

## Abstract

Traffic sign detection under adverse weather conditions remains challenging due to severe feature degradation caused by rain, fog, and snow, which significantly impairs the performance of existing detection systems. This study presents the CW-DETR (Complex Weather Detection Transformer), an end-to-end detection framework designed to address weather-induced feature deterioration in real-time applications. Building upon the RT-DETR, our approach integrates four key innovations: a multipath feature enhancement network (FPFENet) for preserving fine-grained textures, a Multiscale Edge Enhancement Module (MEEM) for combating boundary degradation, an adaptive dual-stream bidirectional feature pyramid network (ADBF-FPN) for cross-scale feature compensation, and a multiscale convolutional gating module (MCGM) for suppressing semantic–spatial confusion. Extensive experiments on the CCTSDB2021 dataset demonstrate that the CW-DETR achieves 69.0% AP and 94.4% AP50, outperforming state-of-the-art real-time detectors by 2.3–5.7 percentage points while maintaining computational efficiency (56.8 GFLOPs). A cross-dataset evaluation on TT100K, the TSRD, CNTSSS, and real-world snow conditions (LNTU-TSD) confirms the robust generalization capabilities of the proposed model. These results establish CW-DETR as an effective solution for all-weather traffic sign detection in intelligent transportation systems.