A decision cognizant Kullback-Leibler divergence
详细信息 查看全文
- 作者：Moacir Pontia ; b ; ponti@usp.br" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Josef Kittlerb ; j.kittler@surrey.ac.uk" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Mateus Rivaa ; mateusriva@usp.br" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Teó ; filo de Camposb ; c ; t.decampos@st-annes.oxon.org" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Cemre Zorb ; c.zor@surrey.ac.uk" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Kullback&ndash ; Leibler divergence ; Divergence clutter ; Classifier incongruence
- 刊名：Pattern Recognition
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：61
- 期：Complete
- 页码：470-478
- 全文大小：2692 K
文摘
- class="listitem" id="list_li0005">
- class="label">•
The decision cognizant Kullback–Leibler divergence is a better statistic to measure classifier (in)congruence.
- class="label">•
Analytic and simulation studies show the new divergence is more robust to minority class clutter.
- class="label">•
Sensitivity to estimation error is lower than that of the classical Kullback–Leibler divergence.