arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.15799cs.LGstat.ML
收藏

条件分类:一种降低计算能耗的方法

Conditional Classification: A Solution for Computational Energy Reduction

George Mason University(乔治梅森大学);University of California, Davis(加州大学戴维斯分校)

Ali Mirzaeian, Sai Manoj, Ashkan Vakil, Houman Homayoun, Avesta Sasan

摘要:

深度卷积神经网络已经在计算机视觉和其他应用中显示出高效率。然而,随着网络深度的增加,计算复杂性呈指数增长。在本文中,我们提出了一种新的解决方案,以减少计算复杂性的卷积神经网络模型用于多类图像分类。我们提出的技术将分类任务分为两个步骤:1)粗粒度分类,其中输入样本在一组超类中分类,2)细粒度分类,其中最终标签在第一步检测到的超类中预测。我们说明,我们提出的分类器可以达到最好的类分类模型报告的准确性水平,具有较低的计算复杂性(浮点数),只激活部分的模型,需要的图像分类。

英文摘要:

Deep convolutional neural networks have shown high efficiency in computer visions and other applications. However, with the increase in the depth of the networks, the computational complexity is growing exponentially. In this paper, we propose a novel solution to reduce the computational complexity of convolutional neural network models used for many class image classification. Our proposed technique breaks the classification task into two steps: 1) coarse-grain classification, in which the input samples are classified among a set of hyper-classes, 2) fine-grain classification, in which the final labels are predicted among those hyper-classes detected at the first step. We illustrate that our proposed classifier can reach the level of accuracy reported by the best in class classification models with less computational complexity (Flop Count) by only activating parts of the model that are needed for the image classification.

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。

↑