Pay "Attention" to Adverse Weather: Weather-aware Attention-based Object Detection

TL;DR

This paper introduces a weather-aware attention framework that adaptively fuses multimodal sensor data at different stages to improve object detection in adverse weather conditions, outperforming existing methods.

Contribution

The proposed Global-Local Attention (GLA) framework uniquely combines early and late-stage fusion with attention mechanisms for adaptive multimodal sensor integration under challenging weather.

Findings

GLA outperforms state-of-the-art fusion methods in adverse weather scenarios.

The framework effectively adjusts sensor weights based on weather conditions.

Experimental results show significant improvements in fog and snow conditions.

Abstract

Despite the recent advances of deep neural networks, object detection for adverse weather remains challenging due to the poor perception of some sensors in adverse weather. Instead of relying on one single sensor, multimodal fusion has been one promising approach to provide redundant detection information based on multiple sensors. However, most existing multimodal fusion approaches are ineffective in adjusting the focus of different sensors under varying detection environments in dynamic adverse weather conditions. Moreover, it is critical to simultaneously observe local and global information under complex weather conditions, which has been neglected in most early or late-stage multimodal fusion works. In view of these, this paper proposes a Global-Local Attention (GLA) framework to adaptively fuse the multi-modality sensing streams, i.e., camera, gated camera, and lidar data, at two fusion stages. Specifically, GLA integrates an early-stage fusion via a local attention network and a late-stage fusion via a global attention network to deal with both local and global information, which automatically allocates higher weights to the modality with better detection features at the late-stage fusion to cope with the specific weather condition adaptively. Experimental results demonstrate the superior performance of the proposed GLA compared with state-of-the-art fusion approaches under various adverse weather conditions, such as light fog, dense fog, and snow.