通过动态裁剪与多维压缩，让边缘设备高效运行复杂图像模型
EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI
- 用轻量级预测器动态裁剪输入图像，只保留关键区域计算
- 同时压缩网络深度、宽度和分辨率，减少48.8%计算量且准确率提升0.8%
- 根据图像难易度自动切换不同模型，适合资源受限的嵌入式部署
卷积神经网络（CNN）在图像分类任务中表现优异，但其高昂的计算成本限制了在资源受限嵌入式设备上的部署。为此，我们提出EdgeCompress，一个全面的压缩框架以降低CNN的计算开销。该框架首先引入动态图像裁剪（DIC），设计轻量级前景预测器，精准裁剪输入图像中最具信息量的前景对象进行推理，避免背景区域的冗余计算。随后提出复合压缩（CS），根据深度、宽度和分辨率对精度与计算量的贡献，协同压缩三维度。DIC与CS共同构成多维压缩框架，从输入图像与网络架构两方面系统减少计算冗余，提升推理效率。进一步提出动态推理框架，将压缩框架中的多个不同复杂度模型级联，根据输入图像识别难度动态选择模型，进一步压缩冗余并提升效率，推动先进CNN在嵌入式硬件上的部署。ImageNet-1K实验表明，EdgeCompress使ResNet-50计算量减少48.8%，同时顶1准确率提升0.8%；相比当前最优压缩方法HRank，在相似计算量下准确率提升4.1%。代码与模型已开源。
原文摘要 · Abstract (English)
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
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。