Disentangling neural mechanisms for perceptual grouping
Disentangling neural mechanisms for perceptual grouping
复制标题
DOI：
10.32470/ccn.2019.1130-0
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Junkyung Kim;Drew Linsley;Kalpit C. Thakkar;Thomas Serre
中科院分区：
文献类型：
--
作者：
Junkyung Kim;Drew Linsley;Kalpit C. Thakkar;Thomas Serre
在视觉场景中形成感知群体和个性化对象是迈向视觉智能的重要一步。这种能力被认为是在大脑中通过自下而上、水平和自上而下的神经元连接实现的计算产生的。然而，人们对这些联系对知觉分组的相对贡献知之甚少。我们通过系统地评估神经网络体系结构来解决这个问题，该体系结构在两个合成视觉任务上以这些连接的组合为特征，强调用于知觉分组的低水平“完形”与高水平对象线索。我们表明，增加任一任务的难度都会使仅依赖自下而上处理的网络的学习变得紧张。水平连接通过支持活动的增量空间传播来解决完形线索任务的这一限制，而自上而下的连接通过传播关于目标对象位置的粗略预测来拯救具有对象线索的任务的学习。我们的发现分离了自下而上、水平和自上而下连接的计算角色，并展示了一个具有所有这些交互作用的模型如何更灵活地学习形成感知小组。
Forming perceptual groups and individuating objects in visual scenes is an essential step towards visual intelligence. This ability is thought to arise in the brain from computations implemented by bottom-up, horizontal, and top-down connections between neurons. However, the relative contributions of these connections to perceptual grouping are poorly understood. We address this question by systematically evaluating neural network architectures featuring combinations of these connections on two synthetic visual tasks, which stress low-level `gestalt' vs. high-level object cues for perceptual grouping. We show that increasing the difficulty of either task strains learning for networks that rely solely on bottom-up processing. Horizontal connections resolve this limitation on tasks with gestalt cues by supporting incremental spatial propagation of activities, whereas top-down connections rescue learning on tasks featuring object cues by propagating coarse predictions about the position of the target object. Our findings disassociate the computational roles of bottom-up, horizontal and top-down connectivity, and demonstrate how a model featuring all of these interactions can more flexibly learn to form perceptual groups.