A feedforward architecture accounts for rapid categorization
A feedforward architecture accounts for rapid categorization
复制标题
DOI：
10.1073/pnas.0700622104
复制
发表时间：
2007-04-10
影响因子：
11.1
通讯作者：
Poggio, Tomaso
中科院分区：
文献类型：
--
作者：
Serre, Thomas;Oliva, Aude;Poggio, Tomaso
灵长类动物在识别物体方面非常擅长。尽管经过了几十年的工程努力，他们的视觉系统的性能水平及其对图像退化的稳健性仍然超过了最好的计算机视觉系统。特别值得注意的是，灵长类动物在超快物体分类和快速连续视觉呈现任务中的高准确率是显著的。考虑到涉及的处理阶段的数量和典型的神经潜伏期，这种快速的视觉处理很可能主要是前馈的。在这里，我们证明了一类对象识别前馈理论的具体实现(该理论扩展了Hubel和Wisel从简单到复杂的细胞层次结构，并考虑了许多解剖学和生理学限制)可以预测人类在快速掩蔽动物与非动物分类任务中取得的成绩水平和模式。
Primates are remarkably good at recognizing objects. The level of performance of their visual system and its robustness to image degradations still surpasses the best computer vision systems despite decades of engineering effort. In particular, the high accuracy of primates in ultra rapid object categorization and rapid serial visual presentation tasks is remarkable. Given the number of processing stages involved and typical neural latencies, such rapid visual processing is likely to be mostly feedforward. Here we show that a specific implementation of a class of feedforward theories of object recognition (that extend the Hubel and Wiesel simple-to-complex cell hierarchy and account for many anatomical and physiological constraints) can predict the level and the pattern of performance achieved by humans on a rapid masked animal vs. non-animal categorization task.