arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.03598cs.AR
收藏

ARMOR:通过模型-硬件协同设计实现鲁棒且高效的基于CNN的SAR ATR

ARMOR: Robust and Efficient CNN-Based SAR ATR through Model-Hardware Co-Design

University of Southern California(南加州大学)

Sachini Wickramasinghe, Tian Ye, Cauligi Raghavendra, Viktor Prasanna

AI总结:

ARMOR通过模型-硬件协同设计,在FPGA平台上实现SAR ATR的鲁棒性和高效性。

摘要:

卷积神经网络(CNNs)在合成孔径雷达(SAR)自动目标识别(ATR)中已取得了最先进的准确率。然而,其高计算成本、延迟和内存占用使其在资源受限的平台上(如小卫星)部署具有挑战性。尽管对抗鲁棒性对实际SAR ATR至关重要,但在系统级优化中往往被忽视。要实现鲁棒性和推理效率,需要一个统一的框架,该框架考虑了对抗训练的模型与硬件约束。我们提出了一种用于基于CNN的SAR ATR的模型-硬件协同设计框架,该框架集成了鲁棒性保持的模型压缩与FPGA加速器设计。压缩阶段包括硬件引导的结构化剪枝,其中从FPGA设计导出的硬件性能模型预测剪枝对延迟和资源使用的影响。这使得能够生成在用户定义的目标下提高硬件效率的帕累托最优模型,同时在预定义的容忍度内保持对抗鲁棒性。我们设计了一种具有通道意识的处理元件(PE)分配的FPGA加速器,支持完全流水线流和时间资源重用架构。自动化的设计生成流程高效地将压缩模型映射到优化的FPGA实现。在广泛使用的MSTAR和FUSAR-Ship数据集上,针对三种CNN架构进行实验,结果显示,我们的框架生成的模型大小可减少高达18.3倍,MAC数量减少3.1倍,同时保持鲁棒性。我们的FPGA实现相比CPU(GPU)基线,推理延迟降低高达68.1倍(6.4倍),能耗效率提高高达169.7倍(33.2倍),证明了所提协同设计框架在FPGA平台上实现鲁棒且高效的SAR ATR的有效性。

英文摘要:

Convolutional Neural Networks (CNNs) have achieved state-of-the-art accuracy in Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR). However, their high computational cost, latency, and memory footprint make its deployment challenging on resource-constrained platforms such as small satellites. While adversarial robustness is critical for real-world SAR ATR, it is often overlooked in system-level optimizations. Achieving both robustness and inference efficiency requires a unified framework that considers adversarially trained models together with hardware constraints. We present a model-hardware co-design framework for CNN-based SAR ATR that integrates robustness-preserving model compression with FPGA accelerator design. The compression stage includes hardware-guided structured pruning, where a hardware performance model derived from the FPGA design predicts the pruning impact on latency and resource usage. This enables the generation of Pareto-optimal models that improve hardware efficiency under user-defined objectives, while maintaining adversarial robustness within a predefined tolerance. We design an FPGA accelerator with channel-aware Processing Element (PE) allocation that supports both fully pipelined streaming and temporal resource-reuse architectures. An automated design generation flow efficiently maps the compressed models to optimized FPGA implementations. Experiments on the widely used MSTAR and FUSAR-Ship datasets across three CNN architectures show that our framework produces models up to 18.3x smaller with 3.1x fewer MACs while preserving robustness. Our FPGA implementation achieves up to 68.1x (6.4x) lower inference latency and up to 169.7x (33.2x) better energy efficiency compared to CPU (GPU) baselines, demonstrating the effectiveness of the proposed co-design framework for robust and efficient SAR ATR on FPGA platforms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑