Home

Awesome

CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor

Shuyang Sun*, Runjia Li*, Philip Torr, Xiuye Gu, Siyang Li

[arXiv] [Project] [Code] [Demo]

The code is fully released at Google Research.

<div align="center"> <img src="https://torrvision.com/images/images_for_pub/clip_as_rnn_teaser.png" width="100%" height="100%"/> </div><br/>

Installation

Requirements

Getting Started

Demo

We have set up an online demo. Currently, the web demo does not support SAM since it's just a CPU-only server. You can check it out at: here

Run Demo Locally

If you want to test an image locally, you can simply run

python3 demo.py --cfg-path=YOUR_CFG_PATH --output_path=SAVE_PATH

Evaluation with Benchmarks

Citing CaR

@inproceedings{clip_as_rnn,
  title = {CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor},
  author = {Sun, Shuyang and Li, Runjia and Torr, Philip and Gu, Xiuye and Li, Siyang},
  year = {2024},
  booktitle = {CVPR},
}