IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification
arXiv:1804.10123
Abstract
Deep residual networks (ResNets) made a recent breakthrough in deep learning. The core idea of ResNets is to have shortcut connections between layers that allow the network to be much deeper while still being easy to optimize avoiding vanishing gradients. These shortcut connections have interesting side-effects that make ResNets behave differently from other typical network architectures. In this work we use these properties to design a network based on a ResNet but with parameter sharing and with adaptive computation time. The resulting network is much smaller than the original network and can adapt the computational cost to the complexity of the input image.
ICLR 2018 Workshop track
References in corpus (8)
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- Residual Networks Behave Like Ensembles of Relatively Shallow Networks
- Adaptive Computation Time for Recurrent Neural Networks
- Highway and Residual Networks learn Unrolled Iterative Estimation
- Residual Connections Encourage Iterative Inference
- Spatially Adaptive Computation Time for Residual Networks
- ShaResNet: reducing residual network parameter number by sharing weights
Cited by in corpus (7)
- Dynamic Neural Networks: A Survey
- EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
- Hidden-Fold Networks: Random Recurrent Residuals Using Sparse Supermasks
- CoDiNet: Path Distribution Modeling with Consistency and Diversity for Dynamic Routing
- Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss
- Adaptive and Iteratively Improving Recurrent Lateral Connections
- Layer Flexible Adaptive Computational Time