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/139/head
Xueyan Zou 2023-10-04 17:07:49 -05:00 committed by GitHub
parent b0c4787775
commit 04037aca23
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 15 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
README.md
View File

@ -4,19 +4,27 @@ We introduce **SEEM** that can **S**egment **E**verything **E**verywhere with **
:grapes: \[[Read our arXiv Paper](https://arxiv.org/pdf/2304.06718.pdf)\]   :apple: \[[Try our Demo](http://semantic-sam.xyzou.net:6090/)\] :grapes: \[[Read our arXiv Paper](https://arxiv.org/pdf/2304.06718.pdf)\]   :apple: \[[Try our Demo](http://semantic-sam.xyzou.net:6090/)\]
**One-Line Demo with Linux:** ## :bookmark_tabs: Catalog
We release the following content for **both SEEM and X-Decoder**:exclamation:
- [x] Demo Code
- [x] Model Checkpoint
- [x] Comprehensive User Guide
- [x] Training Code
- [x] Evaluation Code
:point_right: **One-Line SEEM Demo with Linux:**
```sh ```sh
git clone git@github.com:UX-Decoder/Segment-Everything-Everywhere-All-At-Once.git && sh aasets/scripts/run_demo.sh git clone git@github.com:UX-Decoder/Segment-Everything-Everywhere-All-At-Once.git && sh aasets/scripts/run_demo.sh
``` ```
**Getting Started:** :round_pushpin: *[New]* **Getting Started:**
[INSTALL.md](assets/readmes/INSTALL.md) <br> * [INSTALL.md](assets/readmes/INSTALL.md) <br>
[DATASET.md](assets/readmes/DATASET.md) <br> * [DATASET.md](assets/readmes/DATASET.md) <br>
[TRAIN.md](assets/readmes/TRAIN.md) <br> * [TRAIN.md](assets/readmes/TRAIN.md) <br>
[EVAL.md](assets/readmes/EVAL.md) * [EVAL.md](assets/readmes/EVAL.md)
:point_right: *[New]* **Latest Checkpoints and Numbers:** :round_pushpin: *[New]* **Latest Checkpoints and Numbers:**
| | | | COCO | | | Ref-COCOg | | | VOC | | SBD | | | | | | COCO | | | Ref-COCOg | | | VOC | | SBD | |
|-----------------|---------------------------------------------------------------------------------------------|----------|------|------|------|-----------|------|------|-------|-------|-------|-------| |-----------------|---------------------------------------------------------------------------------------------|----------|------|------|------|-----------|------|------|-------|-------|-------|-------|
| Method | Checkpoint | backbone | PQ &uarr; | mAP &uarr; | mIoU &uarr; | cIoU &uarr; | mIoU &uarr; | AP50 &uarr; | NoC85 &darr; | NoC90 &darr;| NoC85 &darr;| NoC90 &darr;| | Method | Checkpoint | backbone | PQ &uarr; | mAP &uarr; | mIoU &uarr; | cIoU &uarr; | mIoU &uarr; | AP50 &uarr; | NoC85 &darr; | NoC90 &darr;| NoC85 &darr;| NoC90 &darr;|
@ -57,12 +65,6 @@ git clone git@github.com:UX-Decoder/Segment-Everything-Everywhere-All-At-Once.gi
* [X-GPT](https://github.com/microsoft/X-Decoder/tree/xgpt) : Conversational Visual Agent supported by X-Decoder. * [X-GPT](https://github.com/microsoft/X-Decoder/tree/xgpt) : Conversational Visual Agent supported by X-Decoder.
* [LLaVA](https://github.com/haotian-liu/LLaVA) : Large Language and Vision Assistant. * [LLaVA](https://github.com/haotian-liu/LLaVA) : Large Language and Vision Assistant.
## :bookmark_tabs: Catelog
- [x] SEEM Demo
- [x] Inference and Installation Code
- [x] Evaluation Code
- [x] Training Code
## :bulb: Highlights ## :bulb: Highlights
Inspired by the appealing universal interface in LLMs, we are advocating a universal, interactive multi-modal interface for any type of segmentation with **ONE SINGLE MODEL**. We emphasize **4** important features of **SEEM** below. Inspired by the appealing universal interface in LLMs, we are advocating a universal, interactive multi-modal interface for any type of segmentation with **ONE SINGLE MODEL**. We emphasize **4** important features of **SEEM** below.
1. **Versatility**: work with various types of prompts, for example, clicks, boxes, polygons, scribbles, texts, and referring image; 1. **Versatility**: work with various types of prompts, for example, clicks, boxes, polygons, scribbles, texts, and referring image;