弹性神经网络:嵌入式计算机视觉的可扩展框架
Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision
摘要:
我们提出了一个新的框架,图像分类与深度神经网络。该框架将中间输出引入网络的计算图。这使得能够灵活地控制计算负载,并平衡精度和执行时间之间的权衡。此外,我们提出了一个有趣的发现,即中间输出可以在训练时充当正则化器,提高预测精度。在实验部分,我们展示了我们提出的框架在表观年龄估计用例中使用各种常用的预训练深度网络的性能。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。