Channel-Wise Bit Allocation for Deep Visual Feature Quantization

Page view(s)
44
Checked on Jan 09, 2025
Channel-Wise Bit Allocation for Deep Visual Feature Quantization
Title:
Channel-Wise Bit Allocation for Deep Visual Feature Quantization
Journal Title:
2022 IEEE International Conference on Image Processing (ICIP)
Keywords:
Publication Date:
18 October 2022
Citation:
Wang, W., Chen, Z., Wang, Z., Lin, J., Xu, L., & Lin, W. (2022). Channel-Wise Bit Allocation for Deep Visual Feature Quantization. 2022 IEEE International Conference on Image Processing (ICIP). https://doi.org/10.1109/icip46576.2022.9897325
Abstract:
Intermediate deep visual feature compression and transmission is an emerging research topic, which enables a good balance among computing load, bandwidth usage and generalization ability for AI-based visual analysis in edge-cloud collaboration. Quantization and the corresponding ratedistortion optimization are the key techniques in deep feature compression. In this paper, by exploring the feature statistics and a greedy iterative algorithm, we propose a channel-wise bit allocation method for deep feature quantization optimizing for network output error. Given the limited rate and computational power, the proposed method can quantize features with small information loss. Moreover, the method also provides the option to handle the trade-offs between computational cost and quantization performance. Experimental results on ResNet and VGGNet features demonstrate the effectiveness of the proposed bit allocation method.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - AME Young Individual Research Grants (YIRG)
Grant Reference no. : A2084c0176

This research / project is supported by the A*STAR - AI3 HTPO Seed Fund
Grant Reference no. : C211118005
Description:
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISBN:
978-1-6654-9621-6
Files uploaded:

File Size Format Action
3452.pdf 342.09 KB PDF Open