# MaskAdapter
<div align ="center">
<img src="./assets/logo.jpeg" width="20%">
<h1> Mask-Adapter </h1>
<h3> Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation </h3>

YongKang Li<sup>1,\*</sup>, [Tianheng Cheng](https://scholar.google.com/citations?user=PH8rJHYAAAAJ&hl=zh-CN)<sup>1,\*</sup>, [Wenyu Liu](http://eic.hust.edu.cn/professor/liuwenyu)<sup>1</sup>, [Xinggang Wang](https://xwcv.github.io/)<sup>1,📧</sup>

<sup>1</sup> Huazhong University of Science and Technology,


(\* equal contribution, 📧 corresponding author)

[![arxiv paper](https://img.shields.io/badge/arXiv-Paper-red)]()
[![checkpoints](https://img.shields.io/badge/HuggingFace-🤗-orange)]()
[![🤗 HuggingFace Demo](https://img.shields.io/badge/Mask_Adapter-🤗_HF_Demo-orange)]()

</div>


<div align="center">
<img src="./assets/main_fig.png">
</div>

## Highlights

* Mask-Adapter is a simple yet remarkably effective method and can be seamlessly integrated into open-vocabulary segmentation methods, e.g., [FC-CLIP](https://github.com/bytedance/fc-clip) and [MAFT-Plus](https://github.com/jiaosiyu1999/MAFT-Plus), to tackle the existing bottlenecks.

* Mask-Adapter effectively extends to SAM without training, achieving impressive results across multiple open-vocabulary segmentation benchmarks.

## Updates
- [x] Release code
- [x] Release weights
- [x] Release demo with SAM-2👉 [🤗 Mask-Adapter]()
- [ ] Release weights training with addtional data


## Installation
Please follow [installation](INSTALL.md).

## Getting Started

See [Preparing Datasets for Mask-Adapter](datasets/README.md).Following [FC-CLIP](https://github.com/bytedance/fc-clip) and [MAFT-Plus](https://github.com/jiaosiyu1999/MAFT-Plus) to prepare datasets.

See [Getting Started with   Mask-Adapter](GETTING_STARTED.md).



## <a name="Citing Mask-Adapter"></a>Citing  Mask-Adapter

If you use Mask-Adapter in your research, please use the following BibTeX entry.

```BibTeX

```

## Acknowledgement

[Mask2Former](https://github.com/facebookresearch/Mask2Former)

[ODISE](https://github.com/NVlabs/ODISE)

[FC-CLIP](https://github.com/bytedance/fc-clip)

[MAFTP](https://github.com/jiaosiyu1999/MAFT-Plus)

[SAM](https://github.com/facebookresearch/segment-anything)
# MaskAdapter