MiN: Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning (NeurIPS 2025)
September 29, 2025 ยท View on GitHub

How to reproduce our method?
Data
Six datasets are included in our experiments, i.e., CIFAR-100, CUB-200, ImageNet-A, ImageNet-R, FOOD-101 and Omnibenchmark.
- CIFAR-100: it will be automatically downloaded by the code.
- ImageNet-A: official: link
- Omnibenchmark: Onedrive: link
- CUB-200: AWS: link
- FOOD-101: AWS: link
- ImageNet-R: official: link
Then, revise the data path in data_process/data.py.
Install
The core dependencies are as follows:
- torch==2.0.0+cu118 or torch==2.8.0+cu12.8
- torchvision==0.15.1+cu118 or torchvision==0.23.0+cu118
- timm
- scikit-learn
- scipy
How to run?
Use the script "run.sh" to reproduce the restlts of 10 steps setting:
"sh run.sh"
Log Files
We hasv tested our code before uploading. The log files can be found in MiN/log. Due to the equipment change, we have to use 5090 to reproduce our results with torch==2.8.0+cu12.8. The result is basically the same as that stated in the paper.
Main results
CIFAR ViT-B/16-IN21K:

CUB ViT-B/16-IN21K:

IN-A ViT-B/16-IN21K:

IN-R ViT-B/16-IN21K:

FOOD ViT-B/16-IN21K:

Omni. ViT-B/16-IN21K:

If you use any content of this repo for your work, please cite the following bib entries:
@inproceedings{MiN,
title={Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning},
author={Kai Jiang and Zhengyan Shi and Dell Zhang and Hongyuan Zhang and Xuelong Li},
booktitle={The Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS)},
year={2025},
pages={},
}