Skip to content

[TETCI 2025] LightMix: Multi-Objective Search for Lightweight Mixed-Scale Convolutional Neural Networks

License

Notifications You must be signed in to change notification settings

HuangJunh/LightMix

Repository files navigation

LightMix

J. Huang, B. Xue, Y. Sun, M. Zhang, and G. G. Yen, “Lightmix: Multi-objective search for lightweight mixed-scale convolutional neural networks,” IEEE Transactions on Emerging Topics in Computational Intelligence (Early Access), pp. 1–15, 2025. DOI: 10.1109/TETCI.2025.3572041.

📑 Read the Paper

Architecture Search

Specify the hyperparameters for multi-objective evolutionary search and the target dataset in global.ini.

python main.py --gpu 0

Train and Test the Searched Architectures

Specify the hyperparameters for training in main.py and the target script name under ./scripts after architecture search.

python main.py --test --gpu 0 --script_name 'indi-1_00'

Citation

If you use this code in your research, please cite the following paper:

@ARTICLE{LightMix,
  author={Huang, Junhao and Xue, Bing and Sun, Yanan and Zhang, Mengjie and Yen, Gary G.},
  journal={IEEE Transactions on Emerging Topics in Computational Intelligence},
  title={LightMix: Multi-Objective Search for Lightweight Mixed-Scale Convolutional Neural Networks},
  year={2025},
  volume={},
  number={},
  pages={1-15},
  doi={10.1109/TETCI.2025.3572041}}

About

[TETCI 2025] LightMix: Multi-Objective Search for Lightweight Mixed-Scale Convolutional Neural Networks

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages