Multiview Active Learning for Scene Classification with High-Level Semantic-Based Hypothesis Generation

المؤلفون المشاركون

Gu, Yuhong
Yao, Tuozhong
Wang, Wenfeng
Zhu, Qiuguo

المصدر

Scientific Programming

العدد

المجلد 2020، العدد 2020 (31 ديسمبر/كانون الأول 2020)، ص ص. 1-13، 13ص.

الناشر

Hindawi Publishing Corporation

تاريخ النشر

2020-09-01

دولة النشر

مصر

عدد الصفحات

13

التخصصات الرئيسية

الرياضيات

الملخص EN

Multiview active learning (MVAL) is a technique which can result in a large decrease in the size of the version space than traditional active learning and has great potential applications in large-scale data analysis.

This paper made research on MVAL-based scene classification for helping the computer accurately understand diverse and complex environments macroscopically, which has been widely used in many fields such as image retrieval and autonomous driving.

The main contribution of this paper is that different high-level image semantics are used for replacing the traditional low-level features to generate more independent and diverse hypotheses in MVAL.

First, our algorithm uses different object detectors to achieve local object responses in the scenes.

Furthermore, we design a cascaded online LDA model for mining the theme semantic of an image.

The experimental results demonstrate that our proposed theme modeling strategy fits the large-scale data learning, and our MVAL algorithm with both high-level semantic views can achieve significant improvement in the scene classification than traditional active learning-based algorithms.

نمط استشهاد جمعية علماء النفس الأمريكية (APA)

Yao, Tuozhong& Wang, Wenfeng& Gu, Yuhong& Zhu, Qiuguo. 2020. Multiview Active Learning for Scene Classification with High-Level Semantic-Based Hypothesis Generation. Scientific Programming،Vol. 2020, no. 2020, pp.1-13.
https://search.emarefa.net/detail/BIM-1209016

نمط استشهاد الجمعية الأمريكية للغات الحديثة (MLA)

Yao, Tuozhong…[et al.]. Multiview Active Learning for Scene Classification with High-Level Semantic-Based Hypothesis Generation. Scientific Programming No. 2020 (2020), pp.1-13.
https://search.emarefa.net/detail/BIM-1209016

نمط استشهاد الجمعية الطبية الأمريكية (AMA)

Yao, Tuozhong& Wang, Wenfeng& Gu, Yuhong& Zhu, Qiuguo. Multiview Active Learning for Scene Classification with High-Level Semantic-Based Hypothesis Generation. Scientific Programming. 2020. Vol. 2020, no. 2020, pp.1-13.
https://search.emarefa.net/detail/BIM-1209016

نوع البيانات

مقالات

لغة النص

الإنجليزية

الملاحظات

Includes bibliographical references

رقم السجل

BIM-1209016