Weather-Aware Object Detection Transformer for Domain Adaptation

2025-04-15 · Soheil Gharatappeh, Salimeh Sekeh, Vikas Dhiman

RT-DETRs have shown strong performance across various computer vision tasks but are known to degrade under challenging weather conditions such as fog. In this work, we investigate three novel approaches to enhance RT-DETR robustness in foggy environments: (1) Domain Adaptation via Perceptual Loss, which distills domain-invariant features from a teacher network to a student using perceptual supervision; (2) Weather Adaptive Attention, which augments the attention mechanism with fog-sensitive scaling by introducing an auxiliary foggy image stream; and (3) Weather Fusion Encoder, which integrates a dual-stream encoder architecture that fuses clear and foggy image features via multi-head self and cross-attention. Despite the architectural innovations, none of the proposed methods consistently outperform the baseline RT-DETR. We analyze the limitations and potential causes, offering insights for future research in weather-aware object detection.

📄 PDF Abstract BibTeX arXiv:2504.10877

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationObjectobject-detection Object Detection

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

EW-DETR: Evolving World Object Detection via Incremental Low-Rank DEtection TRansformer

2026-02-24 · Munish Monga, Vishal Chudasama, Pankaj Wasnik, C. V. Jawahar arxiv

Real-world object detection must operate in evolving environments where new classes emerge, domains shift, and unseen objects must be identified as "unknown": all without accessing prior data. We introduce Evolving World…

Incremental Learning Domain Adaptation Object Detection

V2X-DGW: Domain Generalization for Multi-agent Perception under Adverse Weather Conditions

2024-03-17 · Baolu Li, Jinlong Li, Xinyu Liu, Runsheng Xu 외

Current LiDAR-based Vehicle-to-Everything (V2X) multi-agent perception systems have shown the significant success on 3D object detection. While these models perform well in the trained clean weather, they struggle in uns…

3D Object Detection Domain Generalization object-detection Object Detection+1

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

2023-09-15 · Minsik Jeon, Junwon Seo, Jihong Min

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 perfor…

Contrastive Learning Domain Adaptation Object object-detection+2

Domain Adaptation based Object Detection for Autonomous Driving in Foggy and Rainy Weather

2023-07-18 · Jinlong Li, Runsheng Xu, Xinyu Liu, Jin Ma 외

Typically, object detection methods for autonomous driving that rely on supervised learning make the assumption of a consistent feature distribution between the training and testing data, this such assumption may fail in…

Autonomous Driving Autonomous Vehicles Data Augmentation Domain Adaptation+3

Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather

2022-10-27 · Jinlong Li, Runsheng Xu, Jin Ma, Qin Zou 외

Most object detection methods for autonomous driving usually assume a consistent feature distribution between training and testing data, which is not always the case when weathers differ significantly. The object detecti…

Autonomous Driving Data Augmentation Domain Adaptation Object+2