论文标题
L-CNN：多发式卷积神经网络的晶格交叉融合策略
L-CNN: A Lattice cross-fusion strategy for multistream convolutional neural networks
论文作者
论文摘要
本文提出了多发式卷积网络（晶格交叉融合）的融合策略。这种方法跨越了卷积层的信号，在合并层之前，在汇总基于数学操作的融合方面。有目的地恶化的CIFAR-10（一种流行的图像分类数据集）的结果，其修改后的Alexnet-LCNN版本表明，这种新方法的表现优于基线单流网络的46％，具有更快的收敛，稳定性和鲁棒性。
This paper proposes a fusion strategy for multistream convolutional networks, the Lattice Cross Fusion. This approach crosses signals from convolution layers performing mathematical operation-based fusions right before pooling layers. Results on a purposely worsened CIFAR-10, a popular image classification data set, with a modified AlexNet-LCNN version show that this novel method outperforms by 46% the baseline single stream network, with faster convergence, stability, and robustness.
