Efficient Learning of Convolution Weights as Gaussian Mixture Model Posteriors
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909237511192576 |
|---|---|
| author | Liang, Lifan |
| author_facet | Liang, Lifan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_17400 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Learning of Convolution Weights as Gaussian Mixture Model Posteriors Liang, Lifan Computer Vision and Pattern Recognition 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. |
| title | Efficient Learning of Convolution Weights as Gaussian Mixture Model Posteriors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.17400 |