-
- KOSUGI Satoshi
- Department of Information and Communication Engineering, The University of Tokyo
-
- YAMASAKI Toshihiko
- Department of Information and Communication Engineering, The University of Tokyo
Search this article
Abstract
<p>Weakly supervised object detection, where a detector is trained with only image-level annotations, is attracting more attention. As a method to obtain a well-performing detector, the detector and the instance labels are updated iteratively. In this study, for more efficient iterative updating, we focus on the instance labeling problem, a problem of which label should be annotated to each region based on the last localization result, and two instance labeling methods are proposed. First, to solve the problem that regions covering only some parts of the object tend to be labeled as positive, we find regions covering the whole object focusing on the context classification loss. Second, considering the situation where the other objects in the image can be labeled as negative, we impose a spatial restriction on regions labeled as negative. Using these methods, we obtain the best results on the PASCAL VOC 2007 and 2012 datasets.</p>
Journal
-
- NIHON GAZO GAKKAISHI (Journal of the Imaging Society of Japan)
-
NIHON GAZO GAKKAISHI (Journal of the Imaging Society of Japan) 59 (6), 585-590, 2020-12-10
The Imaging Society of Japan
- Tweet
Details 詳細情報について
-
- CRID
- 1391694356241821184
-
- NII Article ID
- 130007952865
-
- NII Book ID
- AA1137305X
-
- ISSN
- 18804675
- 13444425
-
- NDL BIB ID
- 031194089
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- NDL
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed