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 2205.04064cs.LGcs.AIcs.CV
收藏

增强:对卷积神经网络有效性的深入了解

Augmentations: An Insight into their Effectiveness on Convolution Neural Networks

Liverpool John Moores University(利物浦约翰摩尔斯大学);Salesforce(赛富时)

Sabeesh Ethiraj, Bharath Kumar Bolla

摘要:

增强是决定任何神经网络性能的关键因素,因为它们为模型提供了提高其性能的关键优势。它们增强模型鲁棒性的能力取决于两个因素,即模型架构和增强类型。增强对于数据集来说是非常特定的,并且并不是所有类型的增强都一定会对模型的性能产生积极的影响。因此,需要识别在各种数据集上表现一致的增强,并且还保持对架构类型、卷积和所使用的参数数量不变。因此,需要识别在各种数据集上表现一致的增强,并且还保持对架构类型、卷积和所使用的参数数量不变。本文评估了使用3x3和深度可分离卷积的参数对MNIST,FMNIST和CIFAR10数据集上不同增强技术的影响。统计证据表明,诸如Curiminal和Random水平翻转的技术在参数化低和高架构上是一致的。深度可分离卷积在更高参数下的性能优于3x3卷积,因为它们能够创建更深的网络。增强导致弥合了3x3和深度可分离卷积之间的准确性差距,从而确立了它们在模型泛化中的作用。在更高的数量扩增并没有产生显着的变化,在性能。还评价了在较高参数下多重增强的协同效应,以及在较低参数下的拮抗效应。这项工作证明,在任何给定的深度学习任务中,需要在架构至上和增强之间实现微妙的平衡,以增强模型的性能。

英文摘要:

Augmentations are the key factor in determining the performance of any neural network as they provide a model with a critical edge in boosting its performance. Their ability to boost a model's robustness depends on two factors, viz-a-viz, the model architecture, and the type of augmentations. Augmentations are very specific to a dataset, and it is not imperative that all kinds of augmentation would necessarily produce a positive effect on a model's performance. Hence there is a need to identify augmentations that perform consistently well across a variety of datasets and also remain invariant to the type of architecture, convolutions, and the number of parameters used. Hence there is a need to identify augmentations that perform consistently well across a variety of datasets and also remain invariant to the type of architecture, convolutions, and the number of parameters used. This paper evaluates the effect of parameters using 3x3 and depth-wise separable convolutions on different augmentation techniques on MNIST, FMNIST, and CIFAR10 datasets. Statistical Evidence shows that techniques such as Cutouts and Random horizontal flip were consistent on both parametrically low and high architectures. Depth-wise separable convolutions outperformed 3x3 convolutions at higher parameters due to their ability to create deeper networks. Augmentations resulted in bridging the accuracy gap between the 3x3 and depth-wise separable convolutions, thus establishing their role in model generalization. At higher number augmentations did not produce a significant change in performance. The synergistic effect of multiple augmentations at higher parameters, with antagonistic effect at lower parameters, was also evaluated. The work proves that a delicate balance between architectural supremacy and augmentations needs to be achieved to enhance a model's performance in any given deep learning task.

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。

↑