|
学习排名的弱监督对象注释转移
Transfer Learning by Ranking for Weakly Supervised Object Annotation |
|
| |
| 课程网址: |
http://videolectures.net/bmvc2012_shi_object_annotation/
|
| 主讲教师: |
Zhiyuan Shi
|
| 开课单位: |
伦敦大学学院
|
| 开课时间: |
2012-10-09
|
| 课程语种: |
英语
|
| 中文简介: |
大多数现有的训练物体探测器的方法依赖于完全监督学习，这需要在训练集中对物体位置进行繁琐的手动注释。最近，人们越来越关注开发弱监督的探测器训练方法，其中对象位置不是手动注释的，而是基于指示训练图像是否包含对象的二进制（弱）标签自动确定的。这是一个具有挑战性的问题，因为每个图像可以包含许多候选对象位置，其部分地与感兴趣对象重叠。现有方法关注于如何最好地利用二进制标签进行对象位置注释。在本文中，我们建议通过将其作为转移学习问题从一个非常不同的角度来解决这个问题。具体而言，我们基于学习排名来制定新颖的转移学习，其有效地将用于对象位置的自动注释的模型从辅助数据集转移到具有完全不相关的对象类别的目标数据集。我们表明，我们的方法优于现有的最先进的弱监督方法，用于在具有挑战性的VOC数据集中注释对象。
|
| 课程简介: |
Most existing approaches to training object detectors rely on fully supervised learning, which requires the tedious manual annotation of object location in a training set. Recently there has been an increasing interest in developing weakly supervised approach to detector training where the object location is not manually annotated but automatically determined based on binary (weak) labels indicating if a training image contains the object. This is a challenging problem because each image can contain many candidate object locations which partially overlaps the object of interest. Existing approaches focus on how to best utilise the binary labels for object location annotation. In this paper we propose to solve this problem from a very different perspective by casting it as a transfer learning problem. Specifically, we formulate a novel transfer learning based on learning to rank, which effectively transfers a model for automatic annotation of object location from an auxiliary dataset to a target dataset with completely unrelated object categories. We show that our approach outperforms existing state-of-the-art weakly supervised approach to annotating objects in the challenging VOC dataset.
|
| 关 键 词: |
全监督学习; 弱监督; 二进制标签; VOC数据集对象
|
| 课程来源: |
视频讲座网
|
| 最后编审: |
2020-10-22：chenxin
|
| 阅读次数: |
41
|
|
图 书 馆