카테고리 계층을 고려한 회선신경망의 이미지 분류

Image Classification Using Convolutional Neural Networks Considering Category Hierarchies

Abstract

In order to improve the performance of image classifications using Convolutional Neural Networks (CNN), applying a category hierarchy to the classification can be a useful idea. However, the visual separation of object categories is very different according to the upper and lower category levels and highly uneven in image classifications. Therefore, it is doubtable whether the use of category hierarchies for classification is effective in CNN. In this paper, we have clarified whether the image classification using category hierarchies improves classification performance, and found at which level of hierarchy classification is more effective. For experiments we divided the image classification task according to the upper and lower category levels and assigned image data to each CNN model. We identified and compared the results of three classification models and analyzed them. Through the experiments, we could confirm that classification effectiveness was not improved by reduction of number of categories in a classification model. And we found that only with the re-training method in the last network layer, the performance of lower category classification was not improved although that of higher category classification was improved.

Fig. 1. Category hierarchy of upper & lower levels.

Fig. 2. Comparison of classification model A and B.

Fig. 3. Comparison of classification model B and C.

Fig. 4. Representative images occur classification errors.

Table 1. Experimental conditions

Table 2. Classification results from Validation sets

Table 3. Classification results from Test sets

Table 4. Comparison of True(T)/False(F) from model B and C

Table 5. Classification errors of model C.1

Table 6. Classification errors of model C affected by failures of model C.1