English

LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification

Computer Vision and Pattern Recognition 2022-04-07 v1 Machine Learning

Abstract

We introduce LilNetX, an end-to-end trainable technique for neural networks that enables learning models with specified accuracy-rate-computation trade-off. Prior works approach these problems one at a time and often require post-processing or multistage training which become less practical and do not scale very well for large datasets or architectures. Our method constructs a joint training objective that penalizes the self-information of network parameters in a reparameterized latent space to encourage small model size while also introducing priors to increase structured sparsity in the parameter space to reduce computation. We achieve up to 50% smaller model size and 98% model sparsity on ResNet-20 while retaining the same accuracy on the CIFAR-10 dataset as well as 35% smaller model size and 42% structured sparsity on ResNet-50 trained on ImageNet, when compared to existing state-of-the-art model compression methods. Code is available at https://github.com/Sharath-girish/LilNetX.

Keywords

Cite

@article{arxiv.2204.02965,
  title  = {LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification},
  author = {Sharath Girish and Kamal Gupta and Saurabh Singh and Abhinav Shrivastava},
  journal= {arXiv preprint arXiv:2204.02965},
  year   = {2022}
}
R2 v1 2026-06-24T10:40:10.601Z