Abstract
In this paper, a novel hierarchical deep network is proposed to combine the deep convolutional neural network and the feature selection-based tree classifier efficiently for image classification. First, the concept ontology is built for organizing large-scale image classes hierarchically in a coarse-to-fine fashion. Second, a novel selective orthogonal algorithm is proposed to make sure deep features extracted for each level classifiers more in line with the requirements of different classification tasks. Also, the role of useful feature components in multi-level deep features are improved. The experimental results on three datasets show that adding a feature selection module in a hierarchical deep network can perform better performance in large-scale image classification.
Highlights
Large -scale object classification has been considered as a challenge problem since very early
The original hand-craft features are very sensitive to the geometric transformation and quality of the image, which is very unfavorable for large-scale image classification
This paper proposes a selective orthogonal algorithm which can select features of hierarchical deep network and make the features extracted by different level classifiers of tree classifier more favorable to perform different classification tasks, and improve the performance of network structure
Summary
Large -scale object classification has been considered as a challenge problem since very early. The hierarchical deep network [12]–[17] combined by deep convolutional neural network [18] and the tree classifier [16] show excellent performance in terms of large-scale object classification. Based on these descriptions [19]–[26], it is very attractive to propose how to use the affiliation between classes in hierarchical deep network. Adding deep learning [1]–[7] in a tree classifier based hierarchical deep network to achieve an end-to-end fashion has achieved outstanding performance on image classes classification.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
