Zero-Shot Unsupervised Transfer Instance Segmentation
Abstract
Segmentation is a core computer vision competency, with applications spanning a broad range of scientifically and economically valuable domains. To date, however, the prohibitive cost of annotation has limited the deployment of flexible segmentation models. In this work, we propose Zero-shot Unsupervised Transfer Instance Segmentation (ZUTIS), a framework that aims to meet this challenge. The key strengths of ZUTIS are: (i) no requirement for instance-level or pixel-level annotations; (ii) an ability of zero-shot transfer, i.e., no assumption on access to a target data distribution; (iii) a unified framework for semantic and instance segmentations with solid performance on both tasks compared to state-or-the art unsupervised methods. While comparing to previous work, we show ZUTIS achieves a gain of 2.2 mask AP on COCO-20K and 14.5 mIoU on ImageNet-S with 919 categories for instance and semantic segmentations, respectively. Code will be made publicly available.1
Cite
Text
Shin et al. "Zero-Shot Unsupervised Transfer Instance Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00513Markdown
[Shin et al. "Zero-Shot Unsupervised Transfer Instance Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/shin2023cvprw-zeroshot/) doi:10.1109/CVPRW59228.2023.00513BibTeX
@inproceedings{shin2023cvprw-zeroshot,
title = {{Zero-Shot Unsupervised Transfer Instance Segmentation}},
author = {Shin, Gyungin and Albanie, Samuel and Xie, Weidi},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2023},
pages = {4848-4858},
doi = {10.1109/CVPRW59228.2023.00513},
url = {https://mlanthology.org/cvprw/2023/shin2023cvprw-zeroshot/}
}