Merged-GHCIDR：一种图像数据压缩的几何方法
Merged-GHCIDR: Geometrical Approach to Reduce Image Data
摘要：
自深度网络出现以来，训练模型所需的计算资源一直在增加。在海量数据集上训练神经网络已经成为一项具有挑战性且耗时的任务。因此，需要在不影响准确性的情况下减少数据集。在本文中，我们提出了新的变化，早期的方法称为减少通过同质聚类减少数据集的大小。所提出的方法是基于将数据集划分为同质聚类并选择对准确性有显着贡献的图像的想法。我们提出了两种变化：几何均匀聚类图像数据缩减（GHCIDR）和合并GHCIDR基于基线算法-通过均匀聚类（RHC）进行缩减，以实现更好的准确性和训练时间。GHCIDR背后的直觉涉及通过训练集的聚类权重和几何分布来选择数据点。Merged-GHCIDR涉及使用完全连锁聚类来合并具有相同标签的聚类。我们使用了三种深度学习模型-全连接网络（FCN）、VGG 1和VGG 16。我们在四个数据集上试验了这两个变体- MNIST，CIFAR 10，Fashion-MNIST和Tiny-Imagenet。具有与RHC相同百分比减少的Merged-GHCIDR在MNIST、Fashion-MNIST、CIFAR 10和Tiny-Imagenet上分别显示出2.8%、8.9%、7.6%和3.5%的准确性增加。
英文摘要：
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.
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。
