Skip to content

horsepurve/iVoro

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 

Repository files navigation

iVoro

Official code for Progressive Voronoi Diagram Subdivision Enables Accurate Data-free Class-Incremental Learning, ICLR'23.

Introduction

The iVoro method is based on the idea of Voronoi Diagram subdivision from Computational Geometry.

A. Establish Voronoi Diagram based on base model.
B. Insertion of a new class as a new Voronoi cell enables the minimal intervention to the overall structure.
C. Divide-and-conquer (a classical algorithm for Voronoi construction) efficiently introduce a batch of new classes into the system.

Results

The results of MNIST in 2D space below clearly showed different space subdivision results from conventional fine-tuning, PASS, and different variants of iVoro.

Reproducing the results

Step 1. Training of the base model, please follow PASS (github).

Step 2. Download the feature files. Google Drive

Go to the directory:

cd MNIST

Then run analysis/CIFAR_voro.py in following order:

A. iVoro B. iVoro-D C. iVoro-AC/AI D. iVoro-L

Reference

ICLR'23

Release

See "Release" page for the codebase. Note that the raw code is provided as is, not cleaned and highly messy. If I had time, I would do some cleaning.

About

ICLR 2023

Resources

Stars

Watchers

Forks

Packages

 
 
 

Contributors

Languages