BAAI
/

WXinlong commited on
Commit
42fbb33
1 Parent(s): d137d5b

first init

Browse files
Files changed (2) hide show
  1. README.md +50 -0
  2. seggpt_teaser.png +0 -0
README.md CHANGED
@@ -1,3 +1,53 @@
1
  ---
2
  license: mit
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: mit
3
  ---
4
+
5
+ <div align="center">
6
+ <h1>SegGPT: Segmenting Everything In Context </h1>
7
+
8
+ [Xinlong Wang](https://www.xloong.wang/)<sup>1*</sup>, &nbsp; [Xiaosong Zhang](https://scholar.google.com/citations?user=98exn6wAAAAJ&hl=en)<sup>1*</sup>, &nbsp; [Yue Cao](http://yue-cao.me/)<sup>1*</sup>, &nbsp; [Wen Wang](https://scholar.google.com/citations?user=1ks0R04AAAAJ&hl)<sup>2</sup>, &nbsp; [Chunhua Shen](https://cshen.github.io/)<sup>2</sup>, &nbsp; [Tiejun Huang](https://scholar.google.com/citations?user=knvEK4AAAAAJ&hl=en)<sup>1,3</sup>
9
+
10
+ <sup>1</sup>[BAAI](https://www.baai.ac.cn/english.html), &nbsp; <sup>2</sup>[ZJU](https://www.zju.edu.cn/english/), &nbsp; <sup>3</sup>[PKU](https://english.pku.edu.cn/)
11
+
12
+ Enjoy the [Demo](https://huggingface.co/spaces/BAAI/SegGPT) and [Code](https://github.com/baaivision/Painter/edit/main/SegGPT)
13
+
14
+
15
+ <br>
16
+
17
+ <image src="seggpt_teaser.png" width="720px" />
18
+ <br>
19
+
20
+ </div>
21
+
22
+ <br>
23
+
24
+ We present SegGPT, a generalist model for segmenting everything in context. With only one single model, SegGPT can perform arbitrary segmentation tasks in images or videos via in-context inference, such as object instance, stuff, part, contour, and text.
25
+ SegGPT is evaluated on a broad range of tasks, including few-shot semantic segmentation, video object segmentation, semantic segmentation, and panoptic segmentation.
26
+ Our results show strong capabilities in segmenting in-domain and out-of-domain targets, either qualitatively or quantitatively.
27
+
28
+ [[Paper]](https://arxiv.org/abs/2304.03284)
29
+ [[Code]](https://github.com/baaivision/Painter/edit/main/SegGPT)
30
+ [[Demo]](https://huggingface.co/spaces/BAAI/SegGPT)
31
+
32
+ ## **Model**
33
+
34
+ A pre-trained SegGPT model is available at [🤗 HF link](https://huggingface.co/BAAI/Painter/blob/main/painter_vit_large.pth).
35
+
36
+
37
+
38
+ ## Citation
39
+
40
+ ```
41
+ @article{SegGPT,
42
+ title={SegGPT: Segmenting Everything In Context},
43
+ author={Wang, Xinlong and Zhang, Xiaosong and Cao, Yue and Wang, Wen and Shen, Chunhua and Huang, Tiejun},
44
+ journal={arXiv preprint arXiv:2304.03284},
45
+ year={2023}
46
+ }
47
+ ```
48
+
49
+ ## Contact
50
+
51
+ **We are hiring** at all levels at BAAI Vision Team, including full-time researchers, engineers and interns.
52
+ If you are interested in working with us on **foundation model, visual perception and multimodal learning**, please contact [Xinlong Wang](https://www.xloong.wang/) (`wangxinlong@baai.ac.cn`) and [Yue Cao](http://yue-cao.me/) (`caoyue@baai.ac.cn`).
53
+
seggpt_teaser.png ADDED