EdgeCompress：用于边缘人工智能的多维模型压缩与动态推理耦合
EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI
AI总结：
研究针对卷积神经网络在嵌入式设备部署的计算成本问题，提出EdgeCompress框架，通过动态图像裁剪和复合收缩进行多维模型压缩，结合动态推理框架，有效减少计算冗余，提高推理效率，实验证明该框架能显著提升模型性能。
摘要：
卷积神经网络（CNNs）在图像分类任务中取得了令人鼓舞的成果。然而，其高昂的计算成本阻碍了在资源受限的嵌入式设备上的部署。为解决此问题，我们提出EdgeCompress，一个全面的压缩框架来减少CNNs的计算开销。首先引入动态图像裁剪（DIC），设计轻量级前景预测器精确裁剪输入图像中最具信息的前景对象以避免背景区域的冗余计算。接着提出复合收缩（CS）根据对精度和模型计算的贡献协同压缩CNNs的三个维度。DIC和CS构成多维压缩框架，还提出动态推理框架，级联不同复杂度模型并针对不同输入图像动态采用不同模型，进一步压缩冗余并提高推理效率。在ImageNet-1K上的实验表明，EdgeCompress将ResNet-50的计算量减少48.8%，同时将top-1准确率提高0.8%，与现有最佳压缩框架HRank相比，在类似计算量下准确率提高4.1%。
英文摘要：
Convolutional neural networks (CNNs) have demonstrated encouraging results in image classification tasks. However, the prohibitive computational cost of CNNs hinders the deployment of CNNs onto resource-constrained embedded devices. To address this issue, we propose EdgeCompress, a comprehensive compression framework to reduce the computational overhead of CNNs. In EdgeCompress, we first introduce dynamic image cropping (DIC), where we design a lightweight foreground predictor to accurately crop the most informative foreground object of input images for inference, which avoids redundant computation on background regions. Subsequently, we present compound shrinking (CS) to collaboratively compress the three dimensions (depth, width, and resolution) of CNNs according to their contribution to accuracy and model computation. DIC and CS together constitute a multidimensional CNN compression framework, which is able to comprehensively reduce the computational redundancy in both input images and neural network architectures, thereby improving the inference efficiency of CNNs. Further, we present a dynamic inference framework to efficiently process input images with different recognition difficulties, where we cascade multiple models with different complexities from our compression framework and dynamically adopt different models for different input images, which further compresses the computational redundancy and improves the inference efficiency of CNNs, facilitating the deployment of advanced CNNs onto embedded hardware. Experiments on ImageNet-1K demonstrate that EdgeCompress reduces the computation of ResNet-50 by 48.8% while improving the top-1 accuracy by 0.8%. Meanwhile, we improve the accuracy by 4.1% with similar computation compared to HRank, the state-of-the-art compression framework. The source code and models are available at https://github.com/ntuliuteam/edge-compress
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。
