论文标题
CIFAR-10使用功能合奏的图像分类
CIFAR-10 Image Classification Using Feature Ensembles
论文作者
论文摘要
图像分类需要生成能够检测图像模式的特征。这项研究的目的是通过利用手动和深度学习方法的不同图像特征来源的组合来对公共CIFAR-10图像数据集进行分类。定向梯度（HOG）和像素强度的直方图成功地为分类提供了信息（分别为53％和59％的分类精度），但有很大的改进空间可以进行。具有成像网训练的权重和CIFAR-10优化模型（CIFAR-VGG）的VGG16进一步改善了图像分类（分别为60％和93.43％的精度）。我们通过利用转移学习来进一步改善分类，以重新建立VGG16（TL-VGG）和Inception Resnet V2（TL-Inception）的最佳网络权重，从而导致绩效的显着提高（分别为85％和90.74％），但未能超越CIFAR-VGG。我们假设，如果每个生成的特征集都获得了对分类问题的独特见解，那么将这些特征组合起来将导致更高的分类精度，从而超过CIFAR-VGG的精度。在选择TL-VGG，TL-Inception，Hog，Pixel强度和CIFAR-VGG的前1000个主要成分后，我们实现了94.6％的测试准确性，对我们的假设提供了支持。
Image classification requires the generation of features capable of detecting image patterns informative of group identity. The objective of this study was to classify images from the public CIFAR-10 image dataset by leveraging combinations of disparate image feature sources from both manual and deep learning approaches. Histogram of oriented gradients (HOG) and pixel intensities successfully inform classification (53% and 59% classification accuracy, respectively), yet there is much room for improvement. VGG16 with ImageNet trained weights and a CIFAR-10 optimized model (CIFAR-VGG) further improve upon image classification (60% and 93.43% accuracy, respectively). We further improved classification by utilizing transfer learning to re-establish optimal network weights for VGG16 (TL-VGG) and Inception ResNet v2 (TL-Inception) resulting in significant performance increases (85% and 90.74%, respectively), yet fail to surpass CIFAR-VGG. We hypothesized that if each generated feature set obtained some unique insight into the classification problem, then combining these features would result in greater classification accuracy, surpassing that of CIFAR-VGG. Upon selection of the top 1000 principal components from TL-VGG, TL-Inception, HOG, pixel intensities, and CIFAR-VGG, we achieved testing accuracy of 94.6%, lending support to our hypothesis.
