轻量化模块+数据剪枝，让边缘设备高效增量学习新类别
LODAP: On-Device Incremental Learning Via Lightweight Operations and Data Pruning
- 用轻量模块和适配器动态学习新类，不增加模型负担
- 在CIFAR-100和Tiny-ImageNet上提升准确率最高4.32%，模型复杂度降50%
- 适合资源受限的边缘设备部署，实测具备实际应用能力
增量学习在模型部署后持续学习新类别，对工业边缘系统尤为重要，因难以频繁连接远程服务器进行密集计算。本文提出LODAP框架，核心为轻量级增量模块（EIM），由普通卷积与轻量操作构成。增量学习时，通过称为适配器的轻量操作高效提取新类特征，提升精度同时降低模型复杂度与训练开销。进一步采用数据剪枝策略，大幅减少训练数据量，降低训练成本。在CIFAR-100和Tiny-ImageNet上实验表明，相比现有方法，准确率最高提升4.32%，模型复杂度约降低50%。真实边缘系统评估验证了其可实用性。代码已公开于https://github.com/duanbiqing/LODAP。
原文摘要 · Abstract (English)
Incremental learning that learns new classes over time after the model's deployment is becoming increasingly crucial, particularly for industrial edge systems, where it is difficult to communicate with a remote server to conduct computation-intensive learning. As more classes are expected to learn after their execution for edge devices. In this paper, we propose LODAP, a new on-device incremental learning framework for edge systems. The key part of LODAP is a new module, namely Efficient Incremental Module (EIM). EIM is composed of normal convolutions and lightweight operations. During incremental learning, EIM exploits some lightweight operations, called adapters, to effectively and efficiently learn features for new classes so that it can improve the accuracy of incremental learning while reducing model complexity as well as training overhead. The efficiency of LODAP is further enhanced by a data pruning strategy that significantly reduces the training data, thereby lowering the training overhead. We conducted extensive experiments on the CIFAR-100 and Tiny- ImageNet datasets. Experimental results show that LODAP improves the accuracy by up to 4.32\% over existing methods while reducing around 50\% of model complexity. In addition, evaluations on real edge systems demonstrate its applicability for on-device machine learning. The code is available at https://github.com/duanbiqing/LODAP.
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。