论文标题
增强：对它们对卷积神经网络有效性的见解
Augmentations: An Insight into their Effectiveness on Convolution Neural Networks
论文作者
论文摘要
增强是确定任何神经网络性能的关键因素，因为它们为提高其性能的模型提供了重要优势。它们提高模型的鲁棒性的能力取决于两个因素，即Viz-a-viz，模型架构和增强的类型。增强非常适合数据集，并且不必必须对模型的性能产生积极影响。因此，有必要确定在各种数据集中始终如一地表现良好的增强，并且对于架构，卷积和所使用的参数数量仍然不变。因此，有必要确定在各种数据集中始终如一地表现良好的增强，并且对于架构，卷积和所使用的参数数量仍然不变。本文使用3x3和深度可分离卷积评估了参数对MNIST，FMNIST和CIFAR10数据集的不同增强技术的影响。统计证据表明，诸如切口和随机水平翻转等技术在参数较低和高体系结构上都是一致的。深度可分离的卷积由于能够创建更深的网络而在更高的参数上优于3x3卷积。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概括中的作用。在较高的数字上，增强并未产生重大的性能变化。还评估了在较高参数下多个增强的协同作用，并在较低的参数下具有拮抗作用。这项工作证明，需要实现建筑至高无上和增强之间的微妙平衡，以在任何给定的深度学习任务中提高模型的表现。
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.
