I want to develop an ensemble approach where the final layer of a CNN model(Flatten layer in this case) will be followed by a K-Means Clustering algorithm where I want to cluster inputs into a number of categories same as required number of categories in a task. I want help regarding how to apply K-Means Clustering with a CNN.
Dear Mohd. Farhan Israk Soumik , you might take this paper here as a blueprint:
Article Analysis of Architecture Combining Convolutional Neural Netw...
And since the authors are here on RG you could maybe direct message them and kindly ask if the code of this project is accessible somewhere in a public repo.
Good luck with your project!
i hope it will be usefully for you https://arxiv.org/ftp/arxiv/papers/1906/1906.03359.pdf
Dear Mohd. Farhan Israk Soumik
Please take a look at the following links, these might be helpful:
https://github.com/MaziarMF/deep-k-means
https://github.com/ASzot/ClusterCNN
Conference Paper Fully convolution neural network combined with K-means clust...
Kind regards,
Cecilia-Irene Loeza-Mejía
If you do a classification task you could just use both classification algorithm k-means and CNN to classify then you'll be more confident about your classification (even better if you use more than just two methods)
- Badges
- Science topic
- Similar topics
- Biological Science
- Bioecology
- Systems Ecology
- Landscape Ecology
- Connectivity