This paper proposes a novel regularization approach to bias Convolutional Neural Networks (CNNs) toward utilizing edge and line features in their hidden layers. Rather than learning arbitrary kernels, we constrain the convolution layers to edge and line detection kernels. This intentional bias regularizes the models, improving generalization performance, especially on small datasets. As a result, test accuracies improve by margins of 5-11 percentage points across four challenging fine-grained classification datasets with limited training data and an identical number of trainable parameters. Instead of traditional convolutional layers, we use Pre-defined Filter Modules, which convolve input data using a fixed set of 3x3 pre-defined edge and line filters. A subsequent ReLU erases information that did not trigger any positive response. Next, a 1x1 convolutional layer generates linear combinations. Notably, the pre-defined filters are a fixed component of the architecture, remaining unchanged during the training phase. Our findings reveal that the number of dimensions spanned by the set of pre-defined filters has a low impact on recognition performance. However, the size of the set of filters matters, with nine or more filters providing optimal results.

翻译：本文提出一种新颖的正则化方法，旨在引导卷积神经网络在其隐藏层中利用边缘与线特征。我们通过约束卷积层使用边缘和线检测核，替代学习任意核的传统方式。这种有意的偏置对模型起到了正则化作用，显著提升了泛化性能，尤其在小型数据集上表现突出。实验结果表明，在四个具有挑战性的细粒度分类数据集（训练数据有限且可训练参数量相同）上，测试准确率提升了5-11个百分点。我们采用预定义滤波模块替代传统卷积层，该模块使用一组固定的3×3预定义边缘与线滤波器对输入数据进行卷积运算。后续的ReLU激活函数将消除未触发任何正向响应的信息。接着通过1×1卷积层生成线性组合。值得注意的是，预定义滤波器作为架构的固定组成部分，在训练阶段始终保持不变。研究发现，预定义滤波器集合所张成的维度数量对识别性能影响较小，但滤波器集合的规模至关重要——当滤波器数量达到九个或以上时，模型可获得最优性能。