English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Network quantization is a powerful technique to compress convolutional neuralnetworks. The quantization granularity determines how to share the scalingfactors in weights, which affects the performance of network quantization. Mostexisting approaches share the scaling factors layerwisely or channelwisely forquantization of convolutional layers. Channelwise quantization and layerwisequantization have been widely used in various applications. However, otherquantization granularities are rarely explored. In this paper, we will explorethe sub-layerwise granularity that shares the scaling factor across multipleinput and output channels. We propose an efficient post-training quantizationmethod in sub-layerwise granularity (PTQ-SL). Then we systematically experimenton various granularities and observe that the prediction accuracy of thequantized neural network has a strong correlation with the granularity.Moreover, we find that adjusting the position of the channels can improve theperformance of sub-layerwise quantization. Therefore, we propose a method toreorder the channels for sub-layerwise quantization. The experimentsdemonstrate that the sub-layerwise quantization with appropriate channelreordering can outperform the channelwise quantization.

PTQ-SL: Exploring the Sub-layerwise Post-training Quantization