Improved Object Categorization and Detection Using Comparative Object Similarity
Improved Object Categorization and Detection Using Comparative Object Similarity
复制标题
DOI：
10.1109/tpami.2013.58
复制
发表时间：
2013-10
影响因子：
23.6
通讯作者：
G. Wang;D. Forsyth;Derek Hoiem
中科院分区：
文献类型：
--
作者：
G. Wang;D. Forsyth;Derek Hoiem
由于真实的世界中对象的固有长尾分布，我们不太可能用每个类别的许多视觉示例来训练对象识别器/检测器。我们必须在对象类别之间共享视觉知识，以便在很少或没有训练示例的情况下进行学习。在本文中，我们表明，当地的对象相似性信息-语句对类别相似或不相似-是一个非常有用的线索，以配合不同的类别，以有效的知识转移。关键的见解：给定一组相似的对象类别和一组不相似的类别，一个好的对象模型应该对来自相似类别的示例的响应比对来自不相似类别的示例的响应更强。为了利用这种依赖于类别的相似性正则化，我们开发了一种正则化的核机器算法来训练核分类器，用于训练样本很少或没有训练样本的类别。我们还采用了最先进的对象检测器来编码对象相似性约束。我们对Labelme数据集上的数百个类别的实验表明，我们的正则化核分类器可以显着提高对象分类。我们还评估了改进的对象检测器的PASCAL VOC 2007基准数据集。
Due to the intrinsic long-tailed distribution of objects in the real world, we are unlikely to be able to train an object recognizer/detector with many visual examples for each category. We have to share visual knowledge between object categories to enable learning with few or no training examples. In this paper, we show that local object similarity information--statements that pairs of categories are similar or dissimilar--is a very useful cue to tie different categories to each other for effective knowledge transfer. The key insight: Given a set of object categories which are similar and a set of categories which are dissimilar, a good object model should respond more strongly to examples from similar categories than to examples from dissimilar categories. To exploit this category-dependent similarity regularization, we develop a regularized kernel machine algorithm to train kernel classifiers for categories with few or no training examples. We also adapt the state-of-the-art object detector to encode object similarity constraints. Our experiments on hundreds of categories from the Labelme dataset show that our regularized kernel classifiers can make significant improvement on object categorization. We also evaluate the improved object detector on the PASCAL VOC 2007 benchmark dataset.