arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.00157cs.CVcs.LG
收藏

L-CNN:一种多流卷积神经网络的格交叉融合策略

L-CNN: A Lattice cross-fusion strategy for multistream convolutional neural networks

Ana Paula G. S. de Almeida, Flavio de Barros Vidal

摘要:

本文提出了一种多流卷积网络的融合策略,格型交叉融合。这种方法交叉来自卷积层的信号,在池化层之前执行基于数学运算的融合。在一个故意恶化的CIFAR-10(一个流行的图像分类数据集)上,使用修改后的AlexNet-LCNN版本的结果表明,这种新方法的性能比基线单流网络高出46%,具有更快的收敛速度,稳定性和鲁棒性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑