In this paper, we showed that the feature map of a convolution layer is equivalent to the unnormalized log posterior of a special kind of Gaussian mixture for image modeling. Then we expanded the model to drive diverse features and proposed a corresponding EM algorithm to learn the model. Learning convolution weights using this approach is efficient, guaranteed to converge, and does not need supervised information. Code is available at: https://github.com/LifanLiang/CALM.
@article{arxiv.2401.17400,
title = {Efficient Learning of Convolution Weights as Gaussian Mixture Model Posteriors},
author = {Lifan Liang},
journal= {arXiv preprint arXiv:2401.17400},
year = {2024}
}