GroupMamba-Tiny Model Card

Model Details

GroupMamba-Tiny is a generic backbone with 23M parameters trained on the ImageNet-1K dataset for vision tasks.

• Model type: Parameter-Efficient and Accurate Vision Backbone Based on Group Visual State Space Model
• License: Non-commercial license

Model Sources

• Repository: https://github.com/amshaker/GroupMamba
• Paper: https://arxiv.org/abs/X.X

Uses

The primary use of GroupMamba is research on vision tasks, e.g., classification, segmentation, detection, and instance segmentation, with an SSM-based backbone. The primary intended users of the model are researchers and hobbyists in computer vision, machine learning, and artificial intelligence.

How to Get Started with the Model

• You can replace the backbone for vision tasks with the proposed GroupMamba: https://github.com/Amshaker/GroupMamba/blob/main/classification/models/groupmamba.py
• Then, you can load this checkpoint and start fine-tuning.

Training Details

GroupMamba is pretrained on ImageNet-1K with classification supervision. The training data is around 1.3M images from ImageNet-1K dataset. See more details in this [paper](https://arxiv.org/abs/X.X.

Evaluation

GroupMamba-Tiny is evaluated on ImageNet-1K val set, and achieves 83.3% Top-1 Acc with only 23M parameters. See more details in this paper.

Additional Information

Citation Information

@article{GroupMamba,
  title={GroupMamba: Parameter-Efficient and Accurate Group Visual State Space Model},
  author={Abdelrahman Shaker and Syed Talal Wasim and Salman Khan and Gall Jürgen and Fahad Khan},
  journal={arXiv preprint arXiv:X.X},
  year={2024}
}