arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.03205cs.CV
收藏

非歧视性数据还是弱模型?关于数据和模型分辨率的相对重要性

Non-discriminative data or weak model? On the relative importance of data and model resolution

Google Research(谷歌研究院)

Mark Sandler, Jonathan Baccash, Andrey Zhmoginov, Andrew Howard

摘要:

我们探讨的问题是,当与隐藏层的分辨率(“内部分辨率”)相比时,输入图像的分辨率(“输入分辨率”)如何影响神经网络的性能。调整这些特性经常被用作超参数,在模型性能和准确性之间提供权衡。一个直观的解释是,低分辨率输入中减少的信息内容导致准确度下降。在本文中,我们表明,在一定程度上,输入分辨率单独对网络性能的作用很小,内部分辨率是模型质量的关键驱动因素。然后,我们在这些见解的基础上开发新的神经网络架构,我们称之为\emph{Isometric Neural Networks}。这些模型在其整个深度内保持固定的内部分辨率。我们证明,他们导致高精度模型与低激活足迹和参数计数。

英文摘要:

We explore the question of how the resolution of the input image ("input resolution") affects the performance of a neural network when compared to the resolution of the hidden layers ("internal resolution"). Adjusting these characteristics is frequently used as a hyperparameter providing a trade-off between model performance and accuracy. An intuitive interpretation is that the reduced information content in the low-resolution input causes decay in the accuracy. In this paper, we show that up to a point, the input resolution alone plays little role in the network performance, and it is the internal resolution that is the critical driver of model quality. We then build on these insights to develop novel neural network architectures that we call \emph{Isometric Neural Networks}. These models maintain a fixed internal resolution throughout their entire depth. We demonstrate that they lead to high accuracy models with low activation footprint and parameter count.

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。

↑