Home

Awesome

Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning

This is the official repository for "Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning."

Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning<br> Xiaojie Li^1, Yibo Yang^2, Jianlong Wu^1, Bernard Ghanem^2, Liqiang Nie^1, Min Zhang^1<br> ^1Harbin Institute of Technology (Shenzhen), ^2King Abdullah University of Science and Technology (KAUST)

Mamba-FSCIL Framework

📒 Updates

🔨 Installation

Follow these steps to set up your environment:

➡️ Data Preparation

🚀 Training

Execute the provided scripts to start training:

CIFAR

sh train_cifar.sh
Session012345678
Mamba-FSCIL82.877.8573.6969.6766.8963.6661.4859.7457.51

[Base Log] [Incremental Log]

Mini Imagenet

sh train_miniimagenet.sh
Session012345678
Mamba-FSCIL84.9380.0274.6171.3369.1565.6262.3860.9359.36

[Base Log] [Incremental Log]

CUB

sh train_cub.sh
Session012345678910
Mamba-FSCIL80.976.2672.9770.1467.8365.7465.4364.1262.3162.1261.65

[Base Log] [Incremental Log]

✏️ Citation

If you find our work useful in your research, please consider citing:

@article{li2024mamba,
  title={Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning},
  author={Li, Xiaojie and Yang, Yibo and Wu, Jianlong and Ghanem, Bernard and Nie, Liqiang and Zhang, Min},
  journal={arXiv preprint arXiv:2407.06136},
  year={2024}
}

👍 Acknowledgments

This codebase builds on FSCIL.Thank you to all the contributors.