請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/62091
標題: | 多重實例迴歸於定界框內物件輪廓之估測 Augmented Multiple Instance Regression For Inferring Object Contours Within Bounding Boxes |
作者: | Kuang-Jui Hsu 許洸睿 |
指導教授: | 莊永裕(Yung-Yu Chuang) |
關鍵字: | 語意式影像切割,弱監督式學習,多重實例迴歸,切割選擇, Semantic segmentation,weakly supervised learning,multiple in- stance regression (MIR),segment selection, |
出版年 : | 2013 |
學位: | 碩士 |
摘要: | In this work, we address the high annotation cost of acquiring training data for semantic segmentation. Most modern approaches utilize graphical models, such as the conditional random fields, to carry out semantic segmentation, and hence rely on sufficient training data in form of object contours. To reduce the manual effort on annotating contours, we consider the training dataset for semantic segmentation is a mixture of a few object contours and an abundant set of bounding boxes of objects. Our idea is to borrow the knowledge derived from the object contours to infer the unknown object contours in the bounding boxes. The inferred contours then can serve as training data. To this end, we generate multiple contour hypotheses for each bounding box with the constraint that at least one hypothesis is close to the ground truth. Corresponding to multiple instance learning (MIL), a bounding box can be treated as a bag with its contour hypotheses as instances. We proposed an approach, called augmented multiple instance regression (AMIR), that formulates the task of hypothesis selection as the problem of MIR, and augments information derived from the object contours to guide and regularize the training process of MIR. The proposed approach is evaluated in the Pascal VOC segmentation task. The experimental results demonstrate that AMIR can precisely infer the object contours in the bounding boxes, and hence provides effective alternates of manually labeled contours for semantic segmentation. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/62091 |
全文授權: | 有償授權 |
顯示於系所單位: | 資訊網路與多媒體研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-102-1.pdf 目前未授權公開取用 | 13.35 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。