Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancement
AAAI 2024
If you like our project, please give us a star โญ on GitHub for latest update.
## ๐ฎ Highlights
* This is the official code of Adaptive FSS, which has been accepted by AAAI 2024.
* It presents a novel FSS framework based on the adapter mechanism that can greatly improve the performance of the current FSS model by adapting it to novel classes.
* Tutorials for training and pre-training weight configuration are placed at [Tutorials](https://github.com/jingw193/AdaptiveFSS/blob/main/tutorial.md)
## ๐ฉ **Updates**
Welcome to **watch** ๐ this repository for the latest updates.
โ
**[2023.12.25]** : Released project page.
โ
**[2023.12.26]** : We have released our paper on Arxiv.
โ
**[2024.1.7]** : Released code.
- [ ] Video release.
## ๐ Experimental Results
### Quantitative Comparison
![](https://github.com/jingw193/AdaptiveFSS/raw/main/assets/Report_score.png)
### Qualitative Comparison
![](https://github.com/jingw193/AdaptiveFSS/raw/main/assets/Vision_comparison.png)
## ๐ **Acknowledgement**
This work is built on many amazing research works and open-source projects, thanks a lot to all the authors for sharing!
* [DCAMA(ECCV2022)](https://github.com/pawn-sxy/DCAMA)
* [FPTrans(NeurIPS2022)](https://github.com/Jarvis73/FPTrans)
* [HDMNet(CVPR2023)](https://github.com/Pbihao/HDMNet)
* [MSANet(2023)](https://github.com/AIVResearch/MSANet)
Besides, this page was built using [Repaint123(2023)](https://github.com/junwuzhang19/repaint123), thanks for the author's sharing!
## โ๏ธ Citation
If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil:.
```BibTeX
@article{Wang_Li_Chen_Zhang_Shen_Zhang_2024,
title={Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancement},
author={Wang Jing and Li Jinagyun and Chen Chen and Zhang Yisi and Shen Haoran and Zhang Tianxiang},
year={2024},
journal={Proceedings of the AAAI Conference on Artificial Intelligence},
month={Feb.},
}
```