Update README.md
Browse files
README.md
CHANGED
|
@@ -8,5 +8,49 @@ base_model:
|
|
| 8 |
# LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model
|
| 9 |
|
| 10 |
|
| 11 |
-
🤗[Data](https://huggingface.co/collections/Senqiao/lisa-67713837a32d6abf516a162e) | 📄[Paper](https://arxiv.org/abs/2312.17240)
|
|
|
|
|
|
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
# LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model
|
| 9 |
|
| 10 |
|
| 11 |
+
🤗[Data](https://huggingface.co/collections/Senqiao/lisa-67713837a32d6abf516a162e) | 📄[Paper](https://arxiv.org/abs/2312.17240) |
|
| 12 |
+
🚀[Code](https://github.com/dvlab-research/LISA/tree/lisa_plus) | 💻[Model](https://huggingface.co/Senqiao/LISA_Plus_7b) |
|
| 13 |
+
🔥[Citation](##citaion)
|
| 14 |
|
| 15 |
+
This model could be used for instance segmentation
|
| 16 |
+
|
| 17 |
+
## Example
|
| 18 |
+
<table class="center">
|
| 19 |
+
<tr>
|
| 20 |
+
<td style="text-align:center;"><b>Input</b></td>
|
| 21 |
+
<td style="text-align:center;"><b>Output</b></td>
|
| 22 |
+
</tr>
|
| 23 |
+
|
| 24 |
+
<tr>
|
| 25 |
+
<td><img src="https://raw.githubusercontent.com/dvlab-research/LISA/lisa_plus/imgs/camera_lens.jpg"></td>
|
| 26 |
+
<td><img src="https://raw.githubusercontent.com/dvlab-research/LISA/lisa_plus/vis_output/camera_lens_masked_img.jpg"></td>
|
| 27 |
+
</tr>
|
| 28 |
+
<tr>
|
| 29 |
+
<td width="50%" style="text-align:center;color:gray;">
|
| 30 |
+
Please describe the two cameras.
|
| 31 |
+
<span style="font-weight: bold; color: #4b8b3b;">+ DEFAULT_INST_CONV_SEG</span>
|
| 32 |
+
</td>
|
| 33 |
+
<td width=50% style="text-align:center;">" The image depicts two vibrant camera models resting on a surface. The larger of the two[ [SEG] ] is situated towards the front of the image, characterized by its prominent lens and sturdy build, indicating it could be a D- sl or E- within the camera brand lineup. The other[ [SEG] ], smaller in size, also a camera, is located further back in the image and is partially obscured by the larger one, characterized by its smaller lens and less prominent features. Both are placed on a surface suggesting they might be on display or in use."</td>
|
| 34 |
+
</tr>
|
| 35 |
+
<tr>
|
| 36 |
+
<td><img src="https://raw.githubusercontent.com/dvlab-research/LISA/lisa_plus/imgs/blackpink.jpg"></td>
|
| 37 |
+
<td><img src="https://raw.githubusercontent.com/dvlab-research/LISA/lisa_plus/vis_output/blackpink_masked_img.jpg"></td>
|
| 38 |
+
</tr>
|
| 39 |
+
<tr>
|
| 40 |
+
<td width="50%" style="text-align:center;color:gray;">
|
| 41 |
+
Please describe the two cameras.
|
| 42 |
+
<span style="font-weight: bold; color: #FF7F50;">+ DEFAULT_INSTANT_SEG</span>
|
| 43 |
+
</td>
|
| 44 |
+
<td width=50% style="text-align:center;">" Sure, [SEG] , [SEG] , [SEG] , and [SEG] ."</td>
|
| 45 |
+
</tr>
|
| 46 |
+
</table>
|
| 47 |
+
|
| 48 |
+
## Citaion
|
| 49 |
+
```
|
| 50 |
+
@article{yang2023lisa++,
|
| 51 |
+
title={Lisa++: An improved baseline for reasoning segmentation with large language model},
|
| 52 |
+
author={Yang, Senqiao and Qu, Tianyuan and Lai, Xin and Tian, Zhuotao and Peng, Bohao and Liu, Shu and Jia, Jiaya},
|
| 53 |
+
journal={arXiv preprint arXiv:2312.17240},
|
| 54 |
+
year={2023}
|
| 55 |
+
}
|
| 56 |
+
```
|