Focused quantization for sparse CNNs
Advances in Neural Information Processing Systems
MetadataShow full item record
Zhao, Y., Gao, X., Bates, D., Mullins, R., & Xu, C. (2021). Focused quantization for sparse CNNs. Advances in Neural Information Processing Systems, 32 https://doi.org/10.17863/CAM.51914
© 2019 Neural information processing systems foundation. All rights reserved. Deep convolutional neural networks (CNNs) are powerful tools for a wide range of vision tasks, but the enormous amount of memory and compute resources required by CNNs pose a challenge in deploying them on constrained devices. Existing compression techniques, while excelling at reducing model sizes, struggle to be computationally friendly. In this paper, we attend to the statistical properties of sparse CNNs and present focused quantization, a novel quantization strategy based on power-of-two values, which exploits the weight distributions after fine-grained pruning. The proposed method dynamically discovers the most effective numerical representation for weights in layers with varying sparsities, significantly reducing model sizes. Multiplications in quantized CNNs are replaced with much cheaper bit-shift operations for efficient inference. Coupled with lossless encoding, we built a compression pipeline that provides CNNs with high compression ratios (CR), low computation cost and minimal loss in accuracy. In ResNet-50, we achieved a 18.08× CR with only 0.24% loss in top-5 accuracy, outperforming existing compression methods. We fully compressed a ResNet-18 and found that it is not only higher in CR and top-5 accuracy, but also more hardware efficient as it requires fewer logic gates to implement when compared to other state-of-the-art quantization methods assuming the same throughput.
This record's DOI: https://doi.org/10.17863/CAM.51914
This record's URL: https://www.repository.cam.ac.uk/handle/1810/304831
All rights reserved