QIANets: Quantum-Integrated Adaptive Networks for Reduced Latency and Improved Inference Times in CNN Models

Zhumazhan Balapanov, Vanessa Matvei, Olivia Holmberg, Edward Magongo, Jonathan Pei +1 more
10/14/2024
cs.CVcs.LG

No official code found. Best implementation: edwardmagongo/Quantum-Inspired-Model-Compression (2 stars, MIT, last commit 2024-10-27).

Abstract

Convolutional neural networks (CNNs) have made significant advances in computer vision tasks, yet their high inference times and latency often limit real-world applicability. While model compression techniques have gained popularity as solutions, they often overlook the critical balance between low latency and uncompromised accuracy. By harnessing quantum-inspired pruning, tensor decomposition, and annealing-based matrix factorization - three quantum-inspired concepts - we introduce QIANets: a novel approach of redesigning the traditional GoogLeNet, DenseNet, and ResNet-18 model architectures to process more parameters and computations whilst maintaining low inference times. Despite experimental limitations, the method was tested and evaluated, demonstrating reductions in inference times, along with effective accuracy preservations.

View on arXivView PDF

Code Implementations(1)

edwardmagongo/Quantum-Inspired-Model-CompressionCommunity100%
MIT

This research explores Quantum-Inspired Model Compression techniques to enhance the efficiency of deep learning models. By leveraging quantum principles, we achieve significant reductions in model size while preserving accuracy. This work presents novel algorithms and compares them to traditional methods. See the README for usage instructions.

22PythonOct 15, 20241 years agoMIT

Similar Papers

LiePrune: Lie Group and Quantum Geometric Dual Representation for One-Shot Structured Pruning of Quantum Neural Networks

85% match2025

Tetra-AML: Automatic Machine Learning via Tensor Networks

85% match2023

Computer Vision Model Compression Techniques for Embedded Systems: A Survey

85% match1 repo82024

Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions

83% match2025

Comprehensive Survey of Model Compression and Speed up for Vision Transformers

83% match2024

ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba

83% match2025

Cite this paper

@article{balapanov2024qianets,
  title  = {QIANets: Quantum-Integrated Adaptive Networks for Reduced Latency and Improved Inference Times in CNN Models},
  author = {Zhumazhan Balapanov and Vanessa Matvei and Olivia Holmberg and Edward Magongo and Jonathan Pei and Kevin Zhu},
  year   = {2024},
  eprint = {2410.10318},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.10318v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.10318.svg)](https://codeofpaper.com/paper/2410.10318)

Discussion