The importance of visual features in generic vs. specialized object recognition: a computational study.
The importance of visual features in generic vs. specialized object recognition: a computational study.
复制标题
DOI：
10.3389/fncom.2014.00078
复制
发表时间：
2014
影响因子：
3.2
通讯作者：
Ebrahimpour R
中科院分区：
文献类型：
--
作者：
Ghodrati M;Rajaei K;Ebrahimpour R
颞下皮层对物体的表征是分布在许多神经元的活动中，还是存在对特定物体反应的有限神经元岛，这一问题一直存在争议。有证据表明梭状回面部区（FFA-in human）处理与特定对象识别相关的信息（这里我们说在类别对象识别，如面部识别）。生理学研究也在猴子的腹侧颞叶中发现了几个负责面部处理的斑块。来自这些斑块的神经元记录表明，神经元对人脸图像具有高度选择性，而对于其他物体，我们在IT中看不到这种选择性。然而，也有很好的证据表明，对象是通过分布式的神经活动模式进行编码的，这些模式对于每个对象类别都是不同的。似乎视觉皮层在类别对象识别（例如，脸与非脸对象）与类别内对象识别（例如，两张不同的脸）之间利用了不同的机制。在这项研究中，我们用计算模拟来解决这个问题。我们使用两个生物学启发的对象识别模型，并定义了两个实验来解决这些问题。模型具有几个处理层的分层结构，这些处理层简单地模拟从V1到aIT的视觉处理。我们通过计算建模表明，这两种识别机制之间的差异可以作为视觉特征和提取机制的基础。为了进行一般和专门的物体识别，视觉皮层必须将类别内和类别间的物体识别机制分离开来。在类内目标识别中，提取中等大小、中等复杂度的类特征可以保证较高的识别性能。然而，通用目标识别需要一个分布式的通用视觉特征字典，其中特征的大小没有显著差异。
It is debated whether the representation of objects in inferior temporal (IT) cortex is distributed over activities of many neurons or there are restricted islands of neurons responsive to a specific set of objects. There are lines of evidence demonstrating that fusiform face area (FFA-in human) processes information related to specialized object recognition (here we say within category object recognition such as face identification). Physiological studies have also discovered several patches in monkey ventral temporal lobe that are responsible for facial processing. Neuronal recording from these patches shows that neurons are highly selective for face images whereas for other objects we do not see such selectivity in IT. However, it is also well-supported that objects are encoded through distributed patterns of neural activities that are distinctive for each object category. It seems that visual cortex utilize different mechanisms for between category object recognition (e.g., face vs. non-face objects) vs. within category object recognition (e.g., two different faces). In this study, we address this question with computational simulations. We use two biologically inspired object recognition models and define two experiments which address these issues. The models have a hierarchical structure of several processing layers that simply simulate visual processing from V1 to aIT. We show, through computational modeling, that the difference between these two mechanisms of recognition can underlie the visual feature and extraction mechanism. It is argued that in order to perform generic and specialized object recognition, visual cortex must separate the mechanisms involved in within category from between categories object recognition. High recognition performance in within category object recognition can be guaranteed when class-specific features with intermediate size and complexity are extracted. However, generic object recognition requires a distributed universal dictionary of visual features in which the size of features does not have significant difference.
登录
查看更多内容
DOI：
10.1126/science.1194908
发表时间：
2010-11-05
期刊：
Science (New York, N.Y.)
影响因子：
--
作者：
Freiwald WA;Tsao DY
通讯作者：
Tsao DY
影响因子：
4.6
作者：
Dahl, Christoph D.;Rasch, Malte J.;Tomonaga, Masaki;Adachi, Ikuma
通讯作者：
Adachi, Ikuma
影响因子：
25
作者：
Freiwald, Winrich A.;Tsao, Doris Y.;Livingstone, Margaret S.
通讯作者：
Livingstone, Margaret S.
影响因子：
64.8
作者：
Epstein, R;Kanwisher, N
通讯作者：
Kanwisher, N
影响因子：
4.1
作者：
DIAMOND, R;CAREY, S
通讯作者：
CAREY, S