This paper introduces two new ensemble-based methods to reduce the data and computation costs of image classification. They can be used with any set of classifiers and do not require additional training. In the first approach, data usage is reduced by only analyzing a full-sized image if the model has low confidence in classifying a low-resolution pixelated version. When applied on the best performing classifiers considered here, data usage is reduced by 61.2% on MNIST, 69.6% on KMNIST, 56.3% on FashionMNIST, 84.6% on SVHN, 40.6% on ImageNet, and 27.6% on ImageNet-V2, all with a less than 5% reduction in accuracy. However, for CIFAR-10, the pixelated data are not particularly informative, and the ensemble approach increases data usage while reducing accuracy. In the second approach, compute costs are reduced by only using a complex model if a simpler model has low confidence in its classification. Computation cost is reduced by 82.1% on MNIST, 47.6% on KMNIST, 72.3% on FashionMNIST, 86.9% on SVHN, 89.2% on ImageNet, and 81.5% on ImageNet-V2, all with a less than 5% reduction in accuracy; for CIFAR-10 the corresponding improvements are smaller at 13.5%. When cost is not an object, choosing the projection from the most confident model for each observation increases validation accuracy to 81.0% from 79.3% for ImageNet and to 69.4% from 67.5% for ImageNet-V2.
翻译:本文引入了两种新的基于集合的方法来降低图像分类的数据和计算成本。它们可与任何一组分类器一起使用,不需要额外的训练。在第一种方法中,只有在模型在对低分辨率像素化版本的分类具有低置信度时,才会分析完整尺寸的图像以减少数据使用。在这里考虑的最佳分类器上应用时,在MNIST上,数据使用减少了61.2%,在KMNIST上减少了69.6%,在FashionMNIST上减少了56.3%,在SVHN上减少了84.6%,在ImageNet上减少了40.6%,在ImageNet-V2上减少了27.6%,而准确度下降不到5%。然而,对于CIFAR-10,像素化数据并不特别说明问题,集合方法会增加数据使用量,同时降低准确度。在第二种方法中,只有在简单模型无法分类时才使用复杂模型,以降低计算成本。在这里考虑的最佳分类器上应用时,在MNIST上,计算成本降低了82.1%,在KMNIST上降低了47.6%,在FashionMNIST上降低了72.3%,在SVHN上降低了86.9%,在ImageNet上降低了89.2%,在ImageNet-V2上降低了81.5%,而准确度下降不到5%。对于CIFAR-10,对应的改进较小,仅为13.5%。当成本不是问题时,选择每个观测值的置信度最高的模型的投影,将ImageNet的验证精度从79.3%提高到81.0%,将ImageNet-V2的精度从67.5%提高到69.4%。