Open-Vocabulary SAM [ECCV-2024]

Haobo Yuan¹, Xiangtai Li¹, Chong Zhou¹, Yining Li², Kai Chen², Chen Change Loy¹.

¹S-Lab, Nanyang Technological University, ²Shanghai Artificial Intelligence Laboratory

RWKV-SAM Arxiv

Haobo Yuan¹, Xiangtai Li^2,1, Tao Zhang², Lu Qi³, Ming-Hsuan Yang³, Shuicheng Yan², Chen Change Loy¹.

¹S-Lab, Nanyang Technological University, ²SkyworkAI ³UC Merced

📰 News

Jul. 2, 2024: Open-Vocabulary SAM has been accepted by ECCV 2024.
Jun. 27, 2024: Release RWKV-SAM code and model Paper. Please check out the folder.

👀 Overview

We introduce the Open-Vocabulary SAM, a SAM-inspired model designed for simultaneous interactive segmentation and recognition, leveraging two unique knowledge transfer modules: SAM2CLIP and CLIP2SAM. The former adapts SAM's knowledge into the CLIP via distillation and learnable transformer adapters, while the latter transfers CLIP knowledge into SAM, enhancing its recognition capabilities.

🔧Usage

To play with Open-Vocabulary SAM, you can:

Try the online demo on the 🤗Hugging Face Space. Thanks for the generous support of the Hugging Face team.

Run the gradio demo locally by cloning and running the repo on 🤗Hugging Face:

git lfs install
git clone https://huggingface.co/spaces/HarborYuan/ovsam ovsam_demo
cd ovsam_demo
conda create -n ovsam_demo python=3.10  && conda activate ovsam_demo
python -m pip install gradio==4.7.1
python -m pip install -r requirements.txt
python main.py

Try to train or evaluate in this repo following the instructions below.

⚙️ Installation

We use conda to manage the environment.

Pytorch installation:

conda install pytorch torchvision torchaudio pytorch-cuda=12.1 cuda -c pytorch  -c "nvidia/label/cuda-12.1.0" -c "nvidia/label/cuda-12.1.1"

mmengine installation:

python -m pip install https://github.com/open-mmlab/mmengine/archive/refs/tags/v0.8.5.zip

mmcv installation (note that older version mmcv before this commit may cause bugs):

TORCH_CUDA_ARCH_LIST="{COMCAP}" TORCH_NVCC_FLAGS="-Xfatbin -compress-all" CUDA_HOME=$(dirname $(dirname $(which nvcc))) LD_LIBRARY_PATH=$(dirname $(dirname $(which nvcc)))/lib MMCV_WITH_OPS=1 FORCE_CUDA=1 python -m pip install git+https://github.com/open-mmlab/mmcv.git@4f65f91db6502d990ce2ee5de0337441fb69dd10

Please ask ChatGPT to get COMCAP:

What is the `Compute Capability` of NVIDIA {YOUR GPU MODEL}? Please only output the number, without text.

Other OpenMMLab packages:

python -m pip install \
https://github.com/open-mmlab/mmdetection/archive/refs/tags/v3.1.0.zip \
https://github.com/open-mmlab/mmsegmentation/archive/refs/tags/v1.1.1.zip \
https://github.com/open-mmlab/mmpretrain/archive/refs/tags/v1.0.1.zip

Extra packages:

python -m pip install git+https://github.com/cocodataset/panopticapi.git \
git+https://github.com/HarborYuan/lvis-api.git \
tqdm terminaltables pycocotools scipy tqdm ftfy regex timm scikit-image kornia

📈 Datasets

Datasets should be put in the data/ folder of this project similar to mmdet. Please prepare dataset in the following format.

COCO dataset

├── coco
│   ├── annotations
│   │   ├── panoptic_{train,val}2017.json
│   │   ├── instance_{train,val}2017.json
│   ├── train2017
│   ├── val2017
│   ├── panoptic_{train,val}2017/  # png annotations

SAM dataset

├── sam
│   ├── train.txt
│   ├── val.txt
│   ├── sa_000020
│   │   ├── sa_223750.jpg
│   │   ├── sa_223750.json
│   │   ├── ...
│   ├── ...

train.txt and val.txt should contain all the folders you need:

sa_000020
sa_000021
...

🚀 Training

Please extract the language embeddings first.

bash tools/dist.sh gen_cls seg/configs/ovsam/ovsam_coco_rn50x16_point.py 8

SAM2CLIP

SAM feature extraction:

bash tools/dist.sh test seg/configs/sam2clip/sam_vith_dump.py 8

SAM2CLIP training:

bash tools/dist.sh train seg/configs/sam2clip/sam2clip_vith_rn50x16.py 8

CLIP2SAM

CLIP2SAM training:

bash tools/dist.sh train seg/configs/clip2sam/clip2sam_coco_rn50x16.py 8

🏃‍♀️Inference

bash tools/dist.sh test seg/configs/ovsam/ovsam_coco_rn50x16_point.py 8

Please refer to 🤗Hugging Face to get the pre-trained weights:

git clone https://huggingface.co/HarborYuan/ovsam_models models

RWKV-SAM

See readme.md for the details.

📚 Citation

If you think our codebases and works are useful for your research, please consider referring us:

@inproceedings{yuan2024ovsam,
    title={Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively},
    author={Yuan, Haobo and Li, Xiangtai and Zhou, Chong and Li, Yining and Chen, Kai and Loy, Chen Change},
    booktitle={ECCV},
    year={2024}
}

@article{yuan2024mamba,
  title={Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model},
  author={Yuan, Haobo and Li, Xiangtai and Qi, Lu and Zhang, Tao and Yang, Ming-Hsuan and Yan, Shuicheng and Loy, Chen Change},
  journal={arXiv preprint},
  year={2024}
}

License

This project is licensed under NTU S-Lab License 1.0. Redistribution and use should follow this license.