|
One-shot learning is an object categorization problem of current research interest in computer vision. Whereas most machine learning based object categorization algorithms require training on hundreds or thousands of images and very large datasets, one-shot learning aims to learn information about object categories from one, or only a few, training images. The primary focus of this article will be on the solution to this problem presented by L. Fei-Fei, R. Fergus and P. Perona in IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol28(4), 2006, which uses a generative object category model and variational Bayesian framework for representation and learning of visual object categories from a handful of training examples. Another paper, presented at the International Conference on Computer Vision and Pattern Recognition (CVPR) 2000 by Erik Miller, Nicholas Matsakis, and Paul Viola will also be discussed. ==Motivation== The ability to learn object categories from few examples, and at a rapid pace, has been demonstrated in humans,〔 F.F. Li et al., 2002〕〔S. Thorpe et al., 1996〕 and it is estimated that a child has learned almost of all the 10 ~ 30 thousand object categories in the world by the age of six.〔Biederman et al., 1987.〕 Yet this achievement of the human mind is due not only to its computational power, but also to its ability to synthesize and learn new object classes from existing information about different, previously learned classes. The images below illustrate the idea that given two examples from two different object classes: one, an unknown object composed of familiar shapes, the second, an unknown, amorphous shape; it is much easier for humans to recognize the former than the latter, suggesting that humans make use of this existing knowledge of previously learned classes when learning new ones. Thus the key motivation and intuition for this one-shot learning technique in the artificial, computational world is that systems, like humans, can use prior information of object categories to learn and classify new objects.〔L. Fei Fei et al., 2006, Section 1〕〔L. Fei-Fei, ''Knowledge transfer'', 2006, Section 1〕 抄文引用元・出典: フリー百科事典『 ウィキペディア（Wikipedia）』 ■ウィキペディアで「One-shot learning」の詳細全文を読む スポンサード リンク
|