Coreset-Based Neural Network Compression
Abstract
We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters. We exploit the redundancies extant in the space of CNN weights and neuronal activations (across samples) in order to obtain compression. Our method requires no retraining, is easy to implement, and obtains state-of-the-art compression performance across a wide variety of CNN architectures. Coupled with quantization and Huffman coding, we create networks that provide AlexNet-like accuracy, with a memory footprint that is $832 imes$ smaller than the original AlexNet, while also introducing significant reductions in inference time as well. Additionally these compressed networks when fine-tuned, successfully generalize to other domains as well.
Cite
Text
Dubey et al. "Coreset-Based Neural Network Compression." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01234-2_28Markdown
[Dubey et al. "Coreset-Based Neural Network Compression." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/dubey2018eccv-coresetbased/) doi:10.1007/978-3-030-01234-2_28BibTeX
@inproceedings{dubey2018eccv-coresetbased,
title = {{Coreset-Based Neural Network Compression}},
author = {Dubey, Abhimanyu and Chatterjee, Moitreya and Ahuja, Narendra},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2018},
doi = {10.1007/978-3-030-01234-2_28},
url = {https://mlanthology.org/eccv/2018/dubey2018eccv-coresetbased/}
}