One-shot learning of object categories
One-shot learning of object categories
复制标题
DOI：
10.1109/tpami.2006.79
复制
发表时间：
2006-04-01
影响因子：
23.6
通讯作者：
Perona, P
中科院分区：
文献类型：
--
作者：
Li, FF;Fergus, R;Perona, P
众所周知，学习对象类别的视觉模型需要数百或数千个训练示例。我们表明，它是可能的，了解更多的信息，从一个类别，或少数，图像。关键的见解是，与其从头开始学习，人们可以利用来自先前学习的类别的知识，无论这些类别可能有多么不同。我们探索贝叶斯实现这一想法。对象类别由概率模型表示。先验知识表示为这些模型的参数的概率密度函数。对象类别的后验模型是通过根据一个或多个观察结果更新先验来获得的。我们测试一个简单的实现我们的算法在数据库中的101个不同的对象类别。我们比较类别模型学习的实现我们的贝叶斯方法的模型学习的最大似然（ML）和最大后验概率（MAP）方法。我们发现，在超过100个类别的数据库中，贝叶斯方法产生的信息模型时，训练样本的数量太小，其他方法无法成功操作。
Learning visual models of object categories notoriously requires hundreds or thousands of training examples. We show that it is possible to learn much information about a category from just one, or a handful, of images. The key insight is that, rather than learning from scratch, one can take advantage of knowledge coming from previously learned categories, no matter how different these categories might be. We explore a Bayesian implementation of this idea. Object categories are represented by probabilistic models. Prior knowledge is represented as a probability density function on the parameters of these models. The posterior model for an object category is obtained by updating the prior in the light of one or more observations. We test a simple implementation of our algorithm on a database of 101 diverse object categories. We compare category models learned by an implementation of our Bayesian approach to models learned from by Maximum Likelihood (ML) and Maximum A Posteriori (MAP) methods. We find that on a database of more than 100 categories, the Bayesian approach produces informative models when the number of training examples is too small for other methods to operate successfully.