让卷积网络像橡皮筋一样伸缩，适配不同设备算力。
Towards Adaptive Deep Learning: Model Elasticity via Prune-and-Grow CNN Architectures
- 通过剪枝生成嵌套子网络，实现模型动态重构
- 在CIFAR-10和Imagenette上保持或提升性能
- 无需重训即可切换大小，适合多设备部署
在资源受限设备上部署深度卷积神经网络（CNN）面临高计算需求与固定架构的挑战。本文提出一种可动态调整计算复杂度的自适应CNN架构，使其在运行时根据硬件资源灵活变化。方法基于结构化剪枝与动态重建，构建单个模型内的嵌套子网络，支持在紧凑与完整配置间无缝切换且无需重新训练。在VGG-16、AlexNet、ResNet-20和ResNet-56等模型上，于CIFAR-10和Imagenette数据集上的实验表明，自适应模型在不同计算约束下均能维持甚至提升性能。结果证明，将适应性直接嵌入架构显著增强模型鲁棒性与灵活性，为多样化计算环境中的高效部署提供新路径。
原文摘要 · Abstract (English)
Deploying deep convolutional neural networks (CNNs) on resource-constrained devices presents significant challenges due to their high computational demands and rigid, static architectures. To overcome these limitations, this thesis explores methods for enabling CNNs to dynamically adjust their computational complexity based on available hardware resources. We introduce adaptive CNN architectures capable of scaling their capacity at runtime, thus efficiently balancing performance and resource utilization. To achieve this adaptability, we propose a structured pruning and dynamic re-construction approach that creates nested subnetworks within a single CNN model. This approach allows the network to dynamically switch between compact and full-sized configurations without retraining, making it suitable for deployment across varying hardware platforms. Experiments conducted across multiple CNN architectures including VGG-16, AlexNet, ResNet-20, and ResNet-56 on CIFAR-10 and Imagenette datasets demonstrate that adaptive models effectively maintain or even enhance performance under varying computational constraints. Our results highlight that embedding adaptability directly into CNN architectures significantly improves their robustness and flexibility, paving the way for efficient real-world deployment in diverse computational environments.
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。