Yi Sun, Jian Li, Xin Xu, Yuru Wang. Depth-Adaptive Dynamic Neural Networks: A Survey[J]. Laser & Optoelectronics Progress, 2022, 59(14): 1415008
- Laser & Optoelectronics Progress
- Vol. 59, Issue 14, 1415008 (2022)
Fig. 1. Depth adaptive neural networks for automatically adjusting inference depth based on the input complexity. (a) Network structure for processing simple input; (b) network structure for processing complex input
Fig. 2. Typical structures of depth-adaptive neural networks. (a) Multi-exit neural network; (b) skip-connection network
Fig. 3. Information exchange scheme of output module
Fig. 4. Network structure MSDNet based on multi-scale down sampling[34]
Fig. 5. Classification accuracy of MSDNet and Ensemble-ResNets on ImageNet dataset[34]
Fig. 6. Basic structure of Gate Module
Fig. 7. Samples with different complexity. (a) Samples with relatively simple texture and background; (b) complex samples
Fig. 8. Shared parameters
Fig. 9. Network structure with dense connection
|
Table 1. Overview about the depth-adaptive neural networks
|
Table 2. Performance comparison of different information fusion approaches on CIFAR100 dataset
|
Table 3. Performance comparison of multi-exit networks trained by knowledge distillation
|
Table 4. Performance comparison of multi-exit networks after using different gradient adjustment approaches on ImageNet dataset
Set citation alerts for the article
Please enter your email address
© Copyright 2018-2021 | Chinese Laser Press. All Rights Reserved 沪ICP备15018463号-20