Sanchez-Cesteros Oscar, Rincon Mariano, Bachiller Margarita, Valladares-Rodriguez Sonia
Department of Artificial Intelligence, National University of Distance Education (UNED), 28040 Madrid, Spain.
Department of Electronics and Computing, University of Santiago de Compostela (USC), 15705 Santiago de Compostela, Spain.
Sensors (Basel). 2023 Aug 31;23(17):7582. doi: 10.3390/s23177582.
Some recent studies show that filters in convolutional neural networks (CNNs) have low color selectivity in datasets of natural scenes such as Imagenet. CNNs, bio-inspired by the visual cortex, are characterized by their hierarchical learning structure which appears to gradually transform the representation space. Inspired by the direct connection between the LGN and V4, which allows V4 to handle low-level information closer to the trichromatic input in addition to processed information that comes from V2/V3, we propose the addition of a long skip connection (LSC) between the first and last blocks of the feature extraction stage to allow deeper parts of the network to receive information from shallower layers. This type of connection improves classification accuracy by combining simple-visual and complex-abstract features to create more color-selective ones. We have applied this strategy to classic CNN architectures and quantitatively and qualitatively analyzed the improvement in accuracy while focusing on color selectivity. The results show that, in general, skip connections improve accuracy, but LSC improves it even more and enhances the color selectivity of the original CNN architectures. As a side result, we propose a new color representation procedure for organizing and filtering feature maps, making their visualization more manageable for qualitative color selectivity analysis.
最近的一些研究表明，卷积神经网络（CNN）中的滤波器在诸如ImageNet等自然场景数据集中具有较低的颜色选择性。CNN受视觉皮层的启发，其特点是具有分层学习结构，这种结构似乎在逐渐变换表示空间。受外侧膝状体（LGN）和V4之间直接连接的启发，该连接使V4除了能处理来自V2/V3的已处理信息外，还能处理更接近三色输入的低级信息，我们建议在特征提取阶段的第一个和最后一个块之间添加一个长跳跃连接（LSC），以使网络的更深部分能够接收来自较浅层的信息。这种连接方式通过结合简单视觉特征和复杂抽象特征来创建更多颜色选择性的特征，从而提高分类准确率。我们已将此策略应用于经典的CNN架构，并在关注颜色选择性的同时，对准确率的提高进行了定量和定性分析。结果表明，一般来说，跳跃连接可提高准确率，但LSC能进一步提高准确率，并增强原始CNN架构的颜色选择性。作为一个附带结果，我们提出了一种新的颜色表示方法，用于组织和过滤特征图，使其可视化更便于进行定性颜色选择性分析。
