论文标题
合并GHCIDR：减少图像数据的几何方法
Merged-GHCIDR: Geometrical Approach to Reduce Image Data
论文作者
论文摘要
自从深层网络成立以来，训练模型所需的计算资源一直在增加。大规模数据集中的培训神经网络已成为一项具有挑战性且耗时的任务。因此，需要减少数据集而不损害准确性。在本文中，我们介绍了一种较早的方法，即通过均匀的聚类来减少数据集大小的新颖方法。所提出的方法基于将数据集划分为均匀簇的想法，并选择对准确性产生显着贡献的图像。我们提出了两种变体：用于图像数据降低的几何均匀聚类（GHCIDR）和合并GHCIDR在基线算法上 - 通过均匀聚类（RHC）降低（RHC），以实现更好的准确性和训练时间。 GHCIDR背后的直觉涉及通过簇权重和训练集的几何分布选择数据点。合并GHCIDR涉及使用完整的链接聚类的群集合并相同的标签。我们使用了三个深度学习模型 - 完全连接的网络（FCN），VGG1和VGG16。我们在四个数据集中的两个变体中进行了实验：MNIST，CIFAR10，Fashion-Mnist和Tiny-Imagenet。与RHC相同百分比的合并GHCIDR在MNIST，Fashion-Mnist，CIFAR10和Tiny-Imagenet上分别增加了2.8％，8.9％，7.6％，7.6％和3.5％。
The computational resources required to train a model have been increasing since the inception of deep networks. Training neural networks on massive datasets have become a challenging and time-consuming task. So, there arises a need to reduce the dataset without compromising the accuracy. In this paper, we present novel variations of an earlier approach called reduction through homogeneous clustering for reducing dataset size. The proposed methods are based on the idea of partitioning the dataset into homogeneous clusters and selecting images that contribute significantly to the accuracy. We propose two variations: Geometrical Homogeneous Clustering for Image Data Reduction (GHCIDR) and Merged-GHCIDR upon the baseline algorithm - Reduction through Homogeneous Clustering (RHC) to achieve better accuracy and training time. The intuition behind GHCIDR involves selecting data points by cluster weights and geometrical distribution of the training set. Merged-GHCIDR involves merging clusters having the same labels using complete linkage clustering. We used three deep learning models- Fully Connected Networks (FCN), VGG1, and VGG16. We experimented with the two variants on four datasets- MNIST, CIFAR10, Fashion-MNIST, and Tiny-Imagenet. Merged-GHCIDR with the same percentage reduction as RHC showed an increase of 2.8%, 8.9%, 7.6% and 3.5% accuracy on MNIST, Fashion-MNIST, CIFAR10, and Tiny-Imagenet, respectively.
