通过相位与幅度交叉调制，提升雷达图像目标检测精度
DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection
- 在变换域中设计注意力机制，实现相位与幅度的联合优化
- 在SARDet-100K上较前代提升0.8%准确率，模型规模减半
- 适合需要高精度雷达目标检测的研究者与工程应用
合成孔径雷达（SAR）目标检测面临相干噪声的普遍干扰。现有方法多通过分析或增强目标的空间域特征来实现隐式去噪。本文提出DenoDet V2，首次从变换域出发，设计新颖注意力架构，利用幅度与相位信息的互补性，通过带级互调机制实现相位与幅度谱的相互增强。相比DenoDet V1，DenoDet V2在多个SAR数据集上表现更优，尤其在SARDet-100K上实现0.8%的精度提升，同时模型复杂度降低50%。代码已开源。
原文摘要 · Abstract (English)
One of the primary challenges in Synthetic Aperture Radar (SAR) object detection lies in the pervasive influence of coherent noise. As a common practice, most existing methods, whether handcrafted approaches or deep learning-based methods, employ the analysis or enhancement of object spatial-domain characteristics to achieve implicit denoising. In this paper, we propose DenoDet V2, which explores a completely novel and different perspective to deconstruct and modulate the features in the transform domain via a carefully designed attention architecture. Compared to DenoDet V1, DenoDet V2 is a major advancement that exploits the complementary nature of amplitude and phase information through a band-wise mutual modulation mechanism, which enables a reciprocal enhancement between phase and amplitude spectra. Extensive experiments on various SAR datasets demonstrate the state-of-the-art performance of DenoDet V2. Notably, DenoDet V2 achieves a significant 0.8\% improvement on SARDet-100K dataset compared to DenoDet V1, while reducing the model complexity by half. The code is available at https://github.com/GrokCV/GrokSAR.
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。