Generalization Boosted Adapter for Open-Vocabulary Segmentation

April 27, 2024 ยท View on GitHub

This repo contains the code for our paper [Generalization Boosted Adapter for Open-Vocabulary Segmentation]


GBA is an universal model for open-vocabulary image segmentation problems, consisting of a class-agnostic segmenter, in-vocabulary classifier, out-of-vocabulary classifier. With everything built upon a shared single frozen convolutional CLIP model,GBA not only achieves state-of-the-art performance on various open-vocabulary segmentation benchmarks, but also enjoys a much lower training (10 days with 4 A6000) and testing costs compared to prior arts.

Installation

See installation instructions.

Getting Started

See Preparing Datasets for GBA.

See Getting Started with GBA.

Acknowledgement

Mask2Former

ODISE

FCCLIP

FreeSeg