We have witnessed the tremendous success of deep neural networks. However, this success comes with the considerable memory and computational costs which make it difficult to deploy these networks directly on resource-constrained embedded systems. To address this problem, we propose TaijiNet, a separable binary network, to reduce the storage and computational overhead while maintaining a comparable accuracy. Furthermore, we also introduce a strategy called partial binarized convolution which binarizes only unimportant kernels to efficiently balance network performance and accuracy. Our approach is evaluated on the CIFAR-10 and ImageNet datasets. The experimental results show that with the proposed TaijiNet, the separable binary versions of AlexNet and ResNet-18 can achieve 26× and 6.4× compression rates with comparable accuracy when comparing with the full-precision versions respectively. In addition, by adjusting the PCA threshold, the xnor version of Taiji-AlexNet improves accuracy by 4-8 percent comparing with other state-of-the-art methods.

中文翻译：

---

嵌入式系统上的可分离二元卷积神经网络

我们见证了深度神经网络的巨大成功。然而，这种成功伴随着相当大的内存和计算成本，这使得很难将这些网络直接部署在资源受限的嵌入式系统上。为了解决这个问题，我们提出了 TaijiNet，一个可分离的二进制网络，以减少存储和计算开销，同时保持可比的准确性。此外，我们还引入了一种称为部分二值化卷积的策略，该策略仅对不重要的内核进行二值化，以有效平衡网络性能和准确性。我们的方法在 CIFAR-10 和 ImageNet 数据集上进行了评估。实验结果表明，使用所提出的 TaijiNet，AlexNet 和 ResNet-18 的可分离二进制版本可以达到 26× 和 6。分别与全精度版本相比，具有可比精度的 4 倍压缩率。此外，通过调整 PCA 阈值，与其他最先进的方法相比，Taiji-AlexNet 的 xnor 版本将准确率提高了 4-8%。