A co-boost framework for learning object categories from Google Images with 1st and 2nd order features
A co-boost framework for learning object categories from Google Images with 1st and 2nd order features
复制标题
用于从 Google 图片中学习具有一阶和二阶特征的对象类别的 co-boost 框架
DOI：
10.1007/s00371-012-0772-2
复制
发表时间：
2012
期刊：
影响因子：
3.5
通讯作者：
Shi, Zhong-Zhi
中科院分区：
文献类型：
--
作者：
Liu, Xi;Shi, Zhi-Ping;Shi, Zhong-Zhi
传统的目标识别技术在很大程度上依赖于人工标注的图像数据集来实现良好的性能。然而，收集高质量的数据集真的很费力。像Google Images这样的图像搜索引擎似乎提供了大量的对象图像。不幸的是，很大一部分搜索图像是无关紧要的。在本文中，我们提出了一个半监督框架，用于从Google图片中学习视觉类别。我们开发了一种协同训练算法CoBoost算法，并将其与一阶和二阶特征相结合，这两种特征分别定义了词包表示和局部特征之间的空间关系。在训练过程中，我们根据一阶和二阶特征创建了两个Boost分类器，其中一个分类器为另一个分类器提供标签。二阶特征是动态生成的，而不是穷举提取，避免了较高的计算量。为了进一步提高性能，还引入了一种主动学习技术。实验结果表明，该方法从Google Images中学习的对象模型在标准基准数据集上与最新的非监督方法和一些监督技术相比具有很好的竞争力。
Conventional object recognition techniques rely heavily on manually annotated image datasets to achieve good performances. However, collecting high quality datasets is really laborious. The image search engines such as Google Images seem to provide quantities of object images. Unfortunately, a large portion of the search images are irrelevant. In this paper, we propose a semi-supervised framework for learning visual categories from Google Images. We exploit a co-training algorithm, the CoBoost algorithm, and integrate it with two kinds of features, the 1st and 2nd order features, which define bag of words representation and spatial relationship between local features, respectively. We create two boosting classifiers based on the 1st and 2nd order features in the training, during which one classifier provides labels for the other. The 2nd order features are generated dynamically rather than extracted exhaustively to avoid high computation. An active learning technique is also introduced to further improve the performance. Experimental results show that the object models learned from Google Images by our method are competitive with the state-of-the-art unsupervised approaches and some supervised techniques on the standard benchmark datasets.
登录
查看更多内容
DOI：
10.1023/b:visi.0000029664.99615.94
发表时间：
2004-11-01
影响因子：
19.5
作者：
Lowe, DG
通讯作者：
Lowe, DG
DOI：
10.1109/iccv.2005.142
发表时间：
2005-10
期刊：
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
影响因子：
--
作者：
R. Fergus;Li Fei-Fei-Li-Fei-Fei-48004138;P. Perona;Andrew Zisserman
通讯作者：
R. Fergus;Li Fei-Fei-Li-Fei-Fei-48004138;P. Perona;Andrew Zisserman
DOI：
10.1007/978-3-540-30115-8_48
发表时间：
2004-09
期刊：
--
影响因子：
--
作者：
Zhi-Hua Zhou;Ke Chen;Yuan Jiang
通讯作者：
Zhi-Hua Zhou;Ke Chen;Yuan Jiang
DOI：
10.1109/tpami.2005.188
发表时间：
2005-10-01
影响因子：
23.6
作者：
Mikolajczyk, K;Schmid, C
通讯作者：
Schmid, C
DOI：
10.1109/cvpr.2008.4587632
发表时间：
2008-06
期刊：
2008 IEEE Conference on Computer Vision and Pattern Recognition
影响因子：
--
作者：
Sudheendra Vijayanarasimhan;K. Grauman
通讯作者：
Sudheendra Vijayanarasimhan;K. Grauman