Learning viewpoint invariant object representations using a temporal coherence principle
Learning viewpoint invariant object representations using a temporal coherence principle
复制标题
DOI：
10.1007/s00422-005-0585-8
复制
发表时间：
2005-07-01
影响因子：
1.9
通讯作者：
König, P
中科院分区：
文献类型：
--
作者：
Einhäuser, W;Hipp, J;König, P
不变目标识别可以说是当代机器视觉系统面临的主要挑战之一。相比之下，哺乳动物的视觉系统几乎毫不费力地完成了这项任务。我们如何利用生物系统的知识来改进人工系统？我们对哺乳动物早期视觉系统的理解已经通过发现一般编码原理可以解释神经元反应特性的许多方面而得到增强。如何将这些方案转换为系统级性能？在目前的研究中，我们训练细胞在一个特定的变种的一般原则的时间相干，“稳定性”的目标。这些细胞在没有教学信号的情况下，在未标记的真实世界图像上进行训练。我们发现，经过训练后，细胞形成了一种很大程度上独立于看待刺激的观点的表征。这一发现包括对以前看不见的观点的概括。所获得的表示比单元格的输入模式更适合于视点不变对象分类。即使训练和分类发生在一个（同样未标记的）干扰对象的存在下，这种促进视点不变分类的特性也保持不变。总之，这里我们展示了使用通用编码原理的无监督学习有助于对现实世界对象进行分类，这些对象没有从背景中分割出来，并且经历了复杂的、非同构的转换。
Invariant object recognition is arguably one of the major challenges for contemporary machine vision systems. In contrast, the mammalian visual system performs this task virtually effortlessly. How can we exploit our knowledge on the biological system to improve artificial systems? Our understanding of the mammalian early visual system has been augmented by the discovery that general coding principles could explain many aspects of neuronal response properties. How can such schemes be transferred to system level performance? In the present study we train cells on a particular variant of the general principle of temporal coherence, the "stability" objective. These cells are trained on unlabeled real-world images without a teaching signal. We show that after training, the cells form a representation that is largely independent of the viewpoint from which the stimulus is looked at. This finding includes generalization to previously unseen viewpoints. The achieved representation is better suited for view-point invariant object classification than the cells' input patterns. This property to facilitate view-point invariant classification is maintained even if training and classification take place in the presence of an - also unlabeled - distractor object. In summary, here we show that unsupervised learning using a general coding principle facilitates the classification of real-world objects, that are not segmented from the background and undergo complex, non-isomorphic, transformations.