Approximating Continuous Convolutions for Deep Network Compression
Approximating Continuous Convolutions for Deep Network Compression
复制标题
DOI：
10.48550/arxiv.2210.08951
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Theo W. Costain;V. Prisacariu
中科院分区：
文献类型：
--
作者：
Theo W. Costain;V. Prisacariu
我们提出了ApproxConv，这是一种压缩卷积神经网络层的新方法。将传统的离散卷积重新定义为空间上参数化函数的连续卷积，我们使用函数逼近来捕获CNN滤波器的基本结构，其参数比传统操作少。我们的方法能够减少训练CNN层的大小，只需要少量的微调。我们证明，我们的方法能够将现有的深度网络模型压缩一半，同时仅损失1.86%的准确率。此外，我们证明了我们的方法与其他压缩方法兼容，如量化，允许进一步减少模型大小。
We present ApproxConv, a novel method for compressing the layers of a convolutional neural network. Reframing conventional discrete convolution as continuous convolution of parametrised functions over space, we use functional approximations to capture the essential structures of CNN filters with fewer parameters than conventional operations. Our method is able to reduce the size of trained CNN layers requiring only a small amount of fine-tuning. We show that our method is able to compress existing deep network models by half whilst losing only 1.86% accuracy. Further, we demonstrate that our method is compatible with other compression methods like quantisation allowing for further reductions in model size.