Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories
Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories
复制标题
DOI：
10.1016/j.cviu.2005.09.012
复制
发表时间：
2007-04-01
影响因子：
4.5
通讯作者：
Perona, Pietro
中科院分区：
文献类型：
--
作者：
Li Fei-Fei;Fergus, Rob;Perona, Pietro
目前用于学习视觉对象类别的计算方法需要数千个训练图像，速度很慢，不能以增量的方式学习，并且不能将先前的信息合并到学习过程中。此外，文献中提出的任何算法都没有在超过几个对象类别上进行测试。我们给出了从几幅训练图像中学习对象类别的所有方法。它是快速的，它以有原则的方式使用先前的信息。我们在一个由101个不同类别的物体的图像组成的数据集上进行了测试。我们提出的方法是基于利用先验信息，这些先验信息是由先前学习的(无关的)对象类别组合而成的。使用生成概率模型，其表示属于对象的特征星座的形状和外观。模型的参数是以贝叶斯方式增量学习的。通过实验比较了我们的增量式算法与早期的批次贝叶斯算法以及基于最大似然的算法。增量版和批处理版在小训练集上的分类性能相当，但增量学习速度明显更快，使得实时学习成为可能。这两种贝叶斯方法在小训练集上的性能都优于最大似然法。(C)2006 Elsevier Inc.保留所有权利。
Current computational approaches to learning visual object categories require thousands of training images, are slow, cannot learn in an incremental manner and cannot incorporate prior information into the learning process. In addition, no algorithm presented in the literature has been tested on more than a handful of object categories. We present all method for learning object categories from just a few training images. It is quick and it uses prior information in a principled way. We test it on a dataset composed of images of objects belonging to 101 widely varied categories. Our proposed method is based on making use of prior information, assembled from (unrelated) object categories which were previously learnt. A generative probabilistic model is used, which represents the shape and appearance of a constellation of features belonging to the object. The parameters of the model are learnt incrementally in a Bayesian manner. Our incremental algorithm is compared experimentally to an earlier batch Bayesian algorithm, as well as to one based on maximum likelihood. The incremental and batch versions have comparable classification performance on small training sets, but incremental learning is significantly faster, making real-time learning feasible. Both Bayesian methods outperform maximum likelihood on small training sets. (C) 2006 Elsevier Inc. All rights reserved.