通过频域与迭代优化提升恶劣天气下的目标检测精度与效率
FR-DETR: Frequency and Recurrent Feature Refinement for Robust Object Detection under Adverse Weather
- 在特征层面而非图像上进行增强，聚焦感兴趣区域
- 频域模块动态分离重加权高低频成分，提升前景背景区分度
- 适合需要高效鲁棒检测的自动驾驶等实际场景
恶劣天气下目标检测因视觉退化和领域偏移仍具挑战。现有基于增强器的方法将增强器与检测器级联，但引入冗余特征提取，计算开销高且与先进检测器结合时精度提升有限。本文提出FR-DETR，一种以检测器为中心的框架，通过特征精炼而非图像增强实现改进。设计两个模块：(I) 频率精炼模块，动态分离并重加权低频与高频成分，提升前景-背景区分能力；(II) 循环聚焦精炼模块（RFRM），利用粗检测结果作为引导，迭代优化特征。大量实验表明，FR-DETR在恶劣天气下实现更优检测精度，同时相比增强器方法显著降低计算开销。
原文摘要 · Abstract (English)
Object detection under adverse weather remains challenging due to severe visual degradations and domain shifts. Existing enhancer-based approaches attempt to improve detection by cascading an enhancer with a detector, but they introduce redundant feature extraction and incur high computational cost with limited accuracy gains when paired with SOTA detectors. We propose FR-DETR, a detector-centric framework that refines features rather than images, focusing enhancement on regions of interest and leveraging frequency-domain cues. Specifically, we design (I) a Frequency Refinement Module that dynamically separates and reweights low- and high-frequency components to improve foreground-background discrimination, and (II) a Recurrent Focus Refinement Module (RFRM) that iteratively refines features using coarse predictions as guidance. Extensive experiments demonstrate that FR-DETR achieves superior detection accuracy under adverse weather while being significantly more computationally efficient than enhancer-based methods. Our implementation is available at https://github.com/ducnt1210/FR-DETR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。