https://github.com/antoniocarta/continual_cd_imm

Implementation of the Class-Domain Infinite Mixture Model from the paper "CD-IMM: The Benefits of Domain-based Mixture Models in Bayesian Continual Learning"
https://github.com/antoniocarta/continual_cd_imm

Last synced: about 1 month ago
JSON representation

Implementation of the Class-Domain Infinite Mixture Model from the paper "CD-IMM: The Benefits of Domain-based Mixture Models in Bayesian Continual Learning"

• Host: GitHub
• URL: https://github.com/antoniocarta/continual_cd_imm
• Owner: AntonioCarta
• Created: 2024-04-29T13:21:34.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-05-29T08:26:15.000Z (8 months ago)
• Last Synced: 2024-10-16T12:44:57.287Z (3 months ago)
• Language: Python
• Size: 146 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# A Bayesian Non-Parametric Classifier for Continual Learning

CN-DPM and the Class VAE reuse the original code. Credits go to the original authors:

- [CN-DPM](https://github.com/soochan-lee/CN-DPM)

- [Class VAE](https://github.com/GMvandeVen/class-incremental-learning)

The Dirichlet Process Mixture Models is a git submodule (available [here](https://github.com/danielecastellana22/torch_dpmm)).