Integrating Flexible Normalization into Midlevel Representations of Deep Convolutional Neural Networks
Integrating Flexible Normalization into Midlevel Representations of Deep Convolutional Neural Networks
复制标题
DOI：
10.1162/neco_a_01226
复制
发表时间：
2019-11-01
影响因子：
2.9
通讯作者：
Schwartz, Odelia
中科院分区：
文献类型：
--
作者：
Giraldo, Luis Gonzalo Sanchez;Schwartz, Odelia
深度卷积神经网络 (CNN) 正成为越来越流行的预测视觉皮层神经反应的模型。然而，当前的 CNN（包括用于神经预测的 CNN）并未明确处理神经处理和感知中普遍存在的上下文效应。在初级视觉皮层中，神经反应以丰富的方式受到空间上围绕经典感受野的刺激的调节。这些效应已使用不同的归一化方法进行建模，包括灵活的模型，其中空间归一化仅在中心和周围位置的响应被视为统计相关的程度上进行。我们提出了一种应用于深度 CNN 中层表示的灵活归一化模型，作为研究中层皮质区域的上下文归一化机制的一种易于处理的方法。这种方法捕获了 CNN 中层特征之间的重要空间依赖性，例如纹理和其他视觉刺激中存在的特征，这些特征是由几何平铺高阶特征产生的。我们期望所提出的方法可以预测何时可以在中层皮质区域招募空间正常化。我们还希望这种方法能够作为 CNN 工具包的一部分发挥作用，从而超越更具限制性的固定形式的标准化。
Deep convolutional neural networks (CNNs) are becoming increasingly popular models to predict neural responses in visual cortex. However, contextual effects, which are prevalent in neural processing and in perception, are not explicitly handled by current CNNs, including those used for neural prediction. In primary visual cortex, neural responses are modulated by stimuli spatially surrounding the classical receptive field in rich ways. These effects have been modeled with divisive normalization approaches, including flexible models, where spatial normalization is recruited only to the degree that responses from center and surround locations are deemed statistically dependent. We propose a flexible normalization model applied to midlevel representations of deep CNNs as a tractable way to study contextual normalization mechanisms in midlevel cortical areas. This approach captures nontrivial spatial dependencies among midlevel features in CNNs, such as those present in textures and other visual stimuli, that arise from tiling high-order features geometrically. We expect that the proposed approach can make predictions about when spatial normalization might be recruited in midlevel cortical areas. We also expect this approach to be useful as part of the CNN tool kit, therefore going beyond more restrictive fixed forms of normalization.