SpikeBottleNet：用于边缘-云协同推理的脉冲驱动特征压缩架构
SpikeBottleNet: Spike-Driven Feature Compression Architecture for Edge-Cloud Co-Inference
AI总结：
提出SpikeBottleNet，一种基于脉冲神经网络的边缘-云协同推理架构，通过SNN激活和编码器-解码器瓶颈实现高达256倍特征压缩，精度损失仅0.16%，能效提升144倍。
摘要：
边缘-云协同推理通过在边缘设备和云服务器之间拆分架构，实现高效的深度神经网络（DNN）部署，这对于资源受限的边缘设备至关重要。该方法需要平衡设备端计算和通信成本，通常通过压缩中间特征传输来实现。传统DNN架构需要连续数据处理和浮点激活，导致相当大的能耗和增大的特征尺寸，从而增加传输成本。这一挑战促使我们探索使用脉冲神经网络（SNN）的二进制、事件驱动激活，SNN以其极高的能效著称。在本研究中，我们提出SpikeBottleNet，一种用于边缘-云协同推理系统的新型架构，它集成了脉冲神经元模型，显著降低边缘设备的能耗。我们研究的一个关键创新是专为SNN设计的中间特征压缩技术，用于高效特征传输。该技术利用拆分计算方法，在ResNet和MobileNet等复杂深度架构中策略性地放置编码器-解码器瓶颈单元。实验结果表明，SpikeBottleNet在ResNet的最终卷积层实现了高达256倍的比特压缩，精度损失极小（0.16%）。此外，与基线BottleNet相比，我们的方法将边缘设备能效提高了高达144倍，使其非常适合资源受限的边缘设备。
英文摘要：
Edge-cloud co-inference enables efficient deep neural network (DNN) deployment by splitting the architecture between an edge device and cloud server, crucial for resource-constraint edge devices. This approach requires balancing on-device computations and communication costs, often achieved through compressed intermediate feature transmission. Conventional DNN architectures require continuous data processing and floating point activations, leading to considerable energy consumption and increased feature sizes, thus raising transmission costs. This challenge motivates exploring binary, event-driven activations using spiking neural networks (SNNs), known for their extreme energy efficiency. In this research, we propose SpikeBottleNet, a novel architecture for edge-cloud co-inference systems that integrates a spiking neuron model to significantly reduce energy consumption on edge devices. A key innovation of our study is an intermediate feature compression technique tailored for SNNs for efficient feature transmission. This technique leverages a split computing approach to strategically place encoder-decoder bottleneck units within complex deep architectures like ResNet and MobileNet. Experimental results demonstrate that SpikeBottleNet achieves up to 256x bit compression in the final convolutional layer of ResNet, with minimal accuracy loss (0.16%). Additionally, our approach enhances edge device energy efficiency by up to 144x compared to the baseline BottleNet, making it ideal for resource-limited edge devices.
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。
