用自监督学习提升雷达图像目标检测，让模型更懂雷达图。
Enhancing SAR Object Detection with Self-Supervised Pre-training on Masked Auto-Encoders
- 用掩码自编码器在雷达图像上做自监督预训练，学出适配雷达特征的表示。
- 在SARDet-100k数据集上比传统方法提升1.3 mAP，增强小样本检测性能。
- 适合做雷达图像目标检测的研究者和工程应用者参考。
监督微调（SFT）在人工智能解析合成孔径雷达（SAR）图像中表现优异，依赖于预训练模型的强大表征能力。然而，缺乏针对SAR图像的领域特定预训练骨干网络，传统方法常采用自然图像（如ImageNet）的预训练模型，其图像特性与SAR图像差异显著，导致在小规模标注的SAR数据上进行SFT时性能受限。本文提出一种基于掩码自编码器（MAE）的自监督学习（SSL）方法，在预训练阶段学习SAR图像的特征表示，以提升后续目标检测任务的表现。在大规模SAR目标检测基准SARDet-100k上的实验验证表明，该方法成功捕捉了SAR图像的潜在特征，通过将预训练域从自然场景转换为雷达图像，提升了模型在下游任务中的泛化能力。相比仅使用SFT的方法，本方法在SARDet-100k上实现了1.3 mAP的提升。
原文摘要 · Abstract (English)
Supervised fine-tuning methods (SFT) perform great efficiency on artificial intelligence interpretation in SAR images, leveraging the powerful representation knowledge from pre-training models. Due to the lack of domain-specific pre-trained backbones in SAR images, the traditional strategies are loading the foundation pre-train models of natural scenes such as ImageNet, whose characteristics of images are extremely different from SAR images. This may hinder the model performance on downstream tasks when adopting SFT on small-scale annotated SAR data. In this paper, an self-supervised learning (SSL) method of masked image modeling based on Masked Auto-Encoders (MAE) is proposed to learn feature representations of SAR images during the pre-training process and benefit the object detection task in SAR images of SFT. The evaluation experiments on the large-scale SAR object detection benchmark named SARDet-100k verify that the proposed method captures proper latent representations of SAR images and improves the model generalization in downstream tasks by converting the pre-trained domain from natural scenes to SAR images through SSL. The proposed method achieves an improvement of 1.3 mAP on the SARDet-100k benchmark compared to only the SFT strategies.
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。