mirrors
/
Segment-Everything-Everywhere-All-At-Once
mirror of https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update README.md

pull/22/head
Jianwei Yang 2023-04-13 17:07:05 -07:00 committed by GitHub
parent beebeb5866
commit d29de10de4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -9,7 +9,7 @@ We introduce **SEEM**, a **S**egment **E**verything **E**verywhere all at Once *
## :dart: Highlights
Inspired by the appealing universal interface in LLM, we are advocating a universal multi-modal interface for visual understanding, in particular segmentation with a SINGLE model! We emphasize **4** important features of **SEEM** here.
Inspired by the appealing universal interface in LLM, we are advocating a universal multi-modal interface for visual understanding, in particular segmentation with a **SINGLE MODEL**! We emphasize **4** important features of **SEEM** here.
1. **Versatility**: work with various types of prompts, for example, clicks, boxes, polygon, scribble, text, and referring image;
2. **Compositionaliy**: deal with any compositions of prompts;
3. **Interactivity**: interact with user multi-rounds because **SEEM** has a memory prompt to store the session history;