Approximating continuous convolutions for deep network compression
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 few...
Main Authors: | Costain, TW, Prisacariu, VA |
---|---|
格式: | Conference item |
语言: | English |
出版: |
British Machine Vision Association
2022
|
相似书籍
-
Approximating continuous convolutions for deep network compression
由: Costain, TW, et al.
出版: (2022) -
Towards generalising neural implicit representations
由: Costain, TW, et al.
出版: (2021) -
Correspondence networks with adaptive neighbourhood consensus
由: Li, S, et al.
出版: (2020) -
Finding non-uniform quantization schemes using multi-task Gaussian processes
由: Gennari do Nascimento, M, et al.
出版: (2020) -
Finding non-uniform quantization schemes using multi-task Gaussian processes
由: Gennari do Nascimento, M, et al.
出版: (2020)