# Subtensor Quantization for Mobilenets

Source: [Subtensor Quantization for Mobilenets](<https://www.sota2.com/research/paper/68fa68bb1e209131cea1ddea>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:04:44.961Z

Authors: Thu Dinh, Andrey Melnikov, Vasilios Daskalopoulos, Sek Chai

Published: 2020-11-04T15:41:47.000Z

## Abstract

Quantization for deep neural networks (DNN) have enabled developers to deploy models with less memory and more efficient low-power inference. However, not all DNN designs are friendly to quantization. For example, the popular Mobilenet architecture has been tuned to reduce parameter size and computational latency with separable depth-wise convolutions, but not all quantization algorithms work well and the accuracy can suffer against its float point versions. In this paper, we analyzed several root causes of quantization loss and proposed alternatives that do not rely on per-channel or training-aware approaches. We evaluate the image classification task on ImageNet dataset, and our post-training quantized 8-bit inference top-1 accuracy in within 0.7% of the floating point version.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2011.08009>)

[PDF](<https://arxiv.org/pdf/2011.08009.pdf>)