Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision
This work addresses the trade-off between accuracy and speed for embedded computer vision applications, presenting an incremental improvement with a novel regularization effect.
The authors tackled the problem of balancing accuracy and execution time in deep neural networks for image classification by introducing intermediate outputs, which improved prediction accuracy and allowed flexible computational control, achieving competitive results in apparent age estimation.
We propose a new framework for image classification with deep neural networks. The framework introduces intermediate outputs to the computational graph of a network. This enables flexible control of the computational load and balances the tradeoff between accuracy and execution time. Moreover, we present an interesting finding that the intermediate outputs can act as a regularizer at training time, improving the prediction accuracy. In the experimental section we demonstrate the performance of our proposed framework with various commonly used pretrained deep networks in the use case of apparent age estimation.