BROWSE
Detail
Conference Paper
Efficient Approximation of Filters for High-Accuracy Binary Convolutional Neural Networks
Cited 0 time in 
Share 
Share
- Authors
- Junyong Park, Yong-Hyuk Moon, Yong-Ju Lee
- Issue Date
- 2020-08
- Citation
- European Conference on Computer Vision (ECCV) 2020 (LNCS 12539), v.12539, pp.71-84
- Publisher
- Springer
- Language
- English
- Type
- Conference Paper
- Abstract
- In this paper, we propose an efficient design to convert full-precision convolutional networks into binary neural networks. Our method approximates a full-precision convolutional filter by sum of binary filters with multiplicative and additive scaling factors. We present closed form solutions to the proposed methods. We perform experiments on binary neural networks with binary activations and pre-trained neural networks with full-precision activations. The results show an increase in accuracy compared to previous binary neural networks. Furthermore, to reduce the complexity, we prune scaling factors considering the accuracy. We show that up혻to a certain degree of threshold, we can prune scaling factors while maintaining accuracy comparable to full-precision convolutional neural networks.
- KSP Keywords
- Convolution neural network(CNN), Convolutional networks, Efficient approximation, High accuracy, closed-form solution, efficient design, neural network(NN), scaling factor