Mask-Adapter / README.md
wondervictor's picture
Rename README copy.md to README.md
30d8526 verified
|
raw
history blame
2.27 kB

MaskAdapter

Mask-Adapter

Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation

YongKang Li1,*, Tianheng Cheng1,*, Wenyu Liu1, Xinggang Wang1,πŸ“§

1 Huazhong University of Science and Technology,

(* equal contribution, πŸ“§ corresponding author)

arxiv paper checkpoints πŸ€— HuggingFace Demo

Highlights

  • Mask-Adapter is a simple yet remarkably effective method and can be seamlessly integrated into open-vocabulary segmentation methods, e.g., FC-CLIP and 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

  • Release code
  • Release weights
  • Release demo with SAM-2πŸ‘‰ πŸ€— Mask-Adapter
  • Release weights training with addtional data

Installation

Please follow installation.

Getting Started

See Preparing Datasets for Mask-Adapter.Following FC-CLIP and MAFT-Plus to prepare datasets.

See Getting Started with Mask-Adapter.

Citing Mask-Adapter

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


Acknowledgement

Mask2Former

ODISE

FC-CLIP

MAFTP

SAM

MaskAdapter