DA-RAW: Domain Adaptive Object Detection for Real-World Adverse Weather Conditions

TL;DR

This paper introduces DA-RAW, an unsupervised domain adaptation framework that improves object detection in adverse weather by separately addressing style and weather gaps, outperforming existing methods.

Contribution

The paper proposes a novel approach that explicitly decomposes and tackles style and weather gaps separately using attention and contrastive learning.

Findings

Outperforms existing methods in adverse weather object detection

Effectively reduces style gap with attention mechanism

Enhances robustness to weather corruption through contrastive learning

Abstract

Despite the success of deep learning-based object detection methods in recent years, it is still challenging to make the object detector reliable in adverse weather conditions such as rain and snow. For the robust performance of object detectors, unsupervised domain adaptation has been utilized to adapt the detection network trained on clear weather images to adverse weather images. While previous methods do not explicitly address weather corruption during adaptation, the domain gap between clear and adverse weather can be decomposed into two factors with distinct characteristics: a style gap and a weather gap. In this paper, we present an unsupervised domain adaptation framework for object detection that can more effectively adapt to real-world environments with adverse weather conditions by addressing these two gaps separately. Our method resolves the style gap by concentrating on style-related information of high-level features using an attention module. Using self-supervised contrastive learning, our framework then reduces the weather gap and acquires instance features that are robust to weather corruption. Extensive experiments demonstrate that our method outperforms other methods for object detection in adverse weather conditions.