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.
@article{arxiv.2508.09392,
title = {DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection},
author = {Kang Ni and Minrui Zou and Yuxuan Li and Xiang Li and Kehua Guo and Ming-Ming Cheng and Yimian Dai},
journal= {arXiv preprint arXiv:2508.09392},
year = {2025}
}