arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.09938cs.CV
收藏

CNN中的每一层都是非平凡的吗?

Is Each Layer Non-trivial in CNN?

Wei Wang, Yanjie Zhu, Zhuoxu Cui, Dong Liang

摘要:

卷积神经网络(CNN)模型在许多领域都取得了巨大的成功。随着ResNet的出现,在实践中使用的网络越来越深入和广泛。然而,网络中的每一层都是非平凡的吗?为了回答这个问题,我们在训练集上训练了一个网络,然后将网络卷积核替换为零,并在测试集上测试结果模型。我们将实验结果与基线进行了比较,结果表明我们可以达到相似甚至相同的性能。虽然卷积核是网络的核心,但我们证明了其中一些在ResNet中是平凡和规则的。

英文摘要:

Convolutional neural network (CNN) models have achieved great success in many fields. With the advent of ResNet, networks used in practice are getting deeper and wider. However, is each layer non-trivial in networks? To answer this question, we trained a network on the training set, then we replace the network convolution kernels with zeros and test the result models on the test set. We compared experimental results with baseline and showed that we can reach similar or even the same performances. Although convolution kernels are the cores of networks, we demonstrate that some of them are trivial and regular in ResNet.

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。

↑