Soft Hough Forest-ERTs: Generalized Hough Transform based object detection from soft-labelled training data
详细信息 查看全文
- 作者：Yingying Liua ; liuy@cse.unsw.edu.au" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Yang Wangb ; yang.wang@nicta.com.au" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Arcot Sowmyaa ; sowmya@cse.unsw.edu.au" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Fang Chena ; b ; fang.chen@nicta.com.au" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Object detection ; Weakly supervised learning ; Generalized Hough Transform ; Extremely Randomized Trees ; Soft labels
- 刊名：Pattern Recognition
- 出版年：2016
- 出版时间：December 2016
- 年：2016
- 卷：60
- 期：Complete
- 页码：145-156
- 全文大小：1691 K
文摘
- •
A modified soft label estimation method by selecting a reliable positive bag based on Maximum Mean Discrepancy.
- •
Extremely Randomized Trees are extended to learn from soft-labelled training blobs.
- •
Probabilistic Hough voting process is derived from soft label ERTs codebook.
- •
Weakly supervised object detection method is proposed.
- •
Experimental results show the advantage of utilizing soft labels, and the performance of the proposed weakly supervised object detection method.