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