Downloads · 30 days
0
VisionLLaMA-Large-MAE
mtgv/VisionLLaMA-Large-MAE
VisionLLaMA-Large-MAE is a image classification model from mtgv. Use it when you need a label for an image. The card lists the license as apache-2.0.
With the Masked Autoencoders' paradigm, VisionLLaMA-Large-MAE model is trained on ImageNet-1K without labels. It retains improvements over classification tasks (SFT, linear probing) on ImageNet-1K.
Access
Public
Updated Mar 13, 2024
Repo size
11.3 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pth11.3 GB · 100%
At a glance
- Task
- Image Classification
- License
- apache-2.0
- Access
- Public
- Created
- Mar 12, 2024
- Updated
- Mar 13, 2024
- SHA
- 69af301f
Datasets
Model card
From the Hugging Face model README
VisionLLaMA-Base-MAE
With the Masked Autoencoders' paradigm, VisionLLaMA-Large-MAE model is trained on ImageNet-1K without labels. It retains improvements over classification tasks (SFT, linear probing) on ImageNet-1K.
| Model | ImageNet Acc (SFT) | ImageNet Acc (Linear Probe) |
|---|---|---|
| VisionLLaMA-Large-MAE (ep800) | 85.5 | 77.3 |
How to Use
Please refer the Github page for usage.
Citation
@article{chu2024visionllama,
title={VisionLLaMA: A Unified LLaMA Interface for Vision Tasks},
author={Chu, Xiangxiang and Su, Jianlin and Zhang, Bo and Shen, Chunhua},
journal={arXiv preprint arXiv:2403.00522},
year={2024}
}
- Task
- Image Classification
- License
- apache-2.0
- Created
- Mar 12, 2024
- Updated
- Mar 13, 2024