# Hybrid Pruning: Thinner Sparse Networks for Fast Inference on Edge Devices

Source: [Hybrid Pruning: Thinner Sparse Networks for Fast Inference on Edge Devices](<https://www.sota2.com/research/paper/68fa65031e209131cea07de7>)

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

Data updated: 2025-10-25T21:16:52.800Z

Authors: Xiaofan Xu, Mi Sun Park, Cormac Brick

Published: 2018-11-01T16:24:50.000Z

## Abstract

We introduce hybrid pruning which combines both coarse-grained channel and fine-grained weight pruning to reduce model size, computation and power demands with no to little loss in accuracy for enabling modern networks deployment on resource-constrained devices, such as always-on security cameras and drones. Additionally, to effectively perform channel pruning, we propose a fast sensitivity test that helps us quickly identify the sensitivity of within and across layers of a network to the output accuracy for target multiplier accumulators (MACs) or accuracy tolerance. Our experiment shows significantly better results on ResNet50 on ImageNet compared to existing work, even with an additional constraint of channels be hardware-friendly number.

## 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/1811.00482>)

[PDF](<https://arxiv.org/pdf/1811.00482.pdf>)