کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6861723 | 1439257 | 2018 | 9 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Combining ontology and reinforcement learning for zero-shot classification
ترجمه فارسی عنوان
ترکیب هستی شناسی و یادگیری تقویت برای طبقه بندی صفر شات
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
هوش مصنوعی
چکیده انگلیسی
Zero-Shot Classification (ZSC) has received much attention recently in computer vision research. Traditional classifiers are unable to handle ZSC because test data labels are significantly different from training data labels. Attribute-based methods have long dominated ZSC. However, classical attribute-based methods fail to distinguish between discriminative attributes and non-discriminative attributes and do not distinguish the different contributions each attribute makes to classification. We propose CORL (Combining Ontology and Reinforcement Learning) for ZSC. CORL first obtains hierarchical classification rules from attribute annotations of object classes based on ontology. These rules contain only discriminative attributes. Reinforcement learning is used to adaptively determine the discriminative degrees of the rules. The most discriminative rules are then selected for ZSC. Experiments on three benchmark datasets showed that CORL achieved higher accuracies than baseline classifiers. This suggests that CORL effectively discovers the most discriminative rules for ZSC.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Knowledge-Based Systems - Volume 144, 15 March 2018, Pages 42-50
Journal: Knowledge-Based Systems - Volume 144, 15 March 2018, Pages 42-50
نویسندگان
Liu Bin, Yao Li, Ding Zheyuan, Xu Junyi, Wu Junfeng,