E$^2$CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning
| Autor: | Alperen Gormez, Venkat R. Dasari, Erdem Koyuncu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| DOI: | 10.48550/arxiv.2103.01148 |
| Popis: | State-of-the-art neural networks with early exit mechanisms often need considerable amount of training and fine tuning to achieve good performance with low computational cost. We propose a novel early exit technique, Early Exit Class Means (E$^2$CM), based on class means of samples. Unlike most existing schemes, E$^2$CM does not require gradient-based training of internal classifiers and it does not modify the base network by any means. This makes it particularly useful for neural network training in low-power devices, as in wireless edge networks. We evaluate the performance and overheads of E$^2$CM over various base neural networks such as MobileNetV3, EfficientNet, ResNet, and datasets such as CIFAR-100, ImageNet, and KMNIST. Our results show that, given a fixed training time budget, E$^2$CM achieves higher accuracy as compared to existing early exit mechanisms. Moreover, if there are no limitations on the training time budget, E$^2$CM can be combined with an existing early exit scheme to boost the latter's performance, achieving a better trade-off between computational cost and network accuracy. We also show that E$^2$CM can be used to decrease the computational cost in unsupervised learning tasks. Comment: 8 pages, 4 figures, 2 tables. Accepted to IJCNN 2022 (WCCI2022) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|