2021
DOI: 10.48550/arxiv.2103.05363
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

MWQ: Multiscale Wavelet Quantized Neural Networks

Abstract: Model quantization can reduce the model size and computational latency, it has become an essential technique for the deployment of deep neural networks on resourceconstrained hardware (e.g., mobile phones and embedded devices). The existing quantization methods mainly consider the numerical elements of the weights and activation values, ignoring the relationship between elements. The decline of representation ability and information loss usually lead to the performance degradation. Inspired by the characterist… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
2
0

Year Published

2021
2021
2022
2022

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 49 publications
0
2
0
Order By: Relevance
“…Using a different transform (known or learned) is also possible, at the corresponding computational cost. [49] introduce quantization in the wavelet domain, as we do in this work. However, the authors suggest to improve the quantization scheme by learning a different clipping parameter per wavelet component, but without the feature shrinkage stage, which is the heart of our approach (we use the same clipping parameter for the whole layer using 8 bits for hardware efficiency).…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…Using a different transform (known or learned) is also possible, at the corresponding computational cost. [49] introduce quantization in the wavelet domain, as we do in this work. However, the authors suggest to improve the quantization scheme by learning a different clipping parameter per wavelet component, but without the feature shrinkage stage, which is the heart of our approach (we use the same clipping parameter for the whole layer using 8 bits for hardware efficiency).…”
Section: Related Workmentioning
confidence: 99%
“…However, the authors suggest to improve the quantization scheme by learning a different clipping parameter per wavelet component, but without the feature shrinkage stage, which is the heart of our approach (we use the same clipping parameter for the whole layer using 8 bits for hardware efficiency). As mentioned before, one can use our WCC together with different types of quantization schemes, in particular including the one proposed by [49], taking the additional hardware complexity of using different clipping parameter per component into account. [3,44,7].…”
Section: Related Workmentioning
confidence: 99%