School of Electrical and Electronics Engineering, Nanyang Technological University, and Advanced Digital Science Center, 37G Nanyang Avenue 04-13, Singapore.
IEEE Trans Pattern Anal Mach Intell. 2013 Oct;35(10):2442-53. doi: 10.1109/TPAMI.2013.58.
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.
由于现实世界中物体的固有长尾分布，我们不太可能为每个类别训练一个具有许多视觉示例的物体识别器/检测器。我们必须在物体类别之间共享视觉知识，以便能够在很少或没有训练示例的情况下进行学习。在本文中，我们表明局部物体相似性信息（将两个类别配对为相似或不相似的陈述）是一个非常有用的线索，可以将不同的类别相互关联，以实现有效的知识转移。关键的见解是：给定一组相似的物体类别和一组不相似的类别，一个好的物体模型应该对相似类别的示例做出比不相似类别的示例更强的响应。为了利用这种基于类别的相似性正则化，我们开发了一种正则化核机器算法，用于训练具有少量或没有训练示例的类别的核分类器。我们还对最先进的物体检测器进行了改编，以编码物体相似性约束。我们在 Labelme 数据集的数百个类别上的实验表明，我们的正则化核分类器可以在物体分类方面取得显著的改进。我们还在 PASCAL VOC 2007 基准数据集上评估了改进后的物体检测器。
