Group-On: Boosting One-Shot Segmentation with Supportive Query
- URL: http://arxiv.org/abs/2404.11871v1
- Date: Thu, 18 Apr 2024 03:10:04 GMT
- Title: Group-On: Boosting One-Shot Segmentation with Supportive Query
- Authors: Hanjing Zhou, Mingze Yin, JinTai Chen, Danny Chen, Jian Wu,
- Abstract summary: One-shot semantic segmentation aims to segment query images given only ONE annotated support image of the same class.
We propose a novel approach for ONE-shot semantic segmentation, called Group-On, which packs multiple query images in batches.
- Score: 8.623405412540247
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: One-shot semantic segmentation aims to segment query images given only ONE annotated support image of the same class. This task is challenging because target objects in the support and query images can be largely different in appearance and pose (i.e., intra-class variation). Prior works suggested that incorporating more annotated support images in few-shot settings boosts performances but increases costs due to additional manual labeling. In this paper, we propose a novel approach for ONE-shot semantic segmentation, called Group-On, which packs multiple query images in batches for the benefit of mutual knowledge support within the same category. Specifically, after coarse segmentation masks of the batch of queries are predicted, query-mask pairs act as pseudo support data to enhance mask predictions mutually, under the guidance of a simple Group-On Voting module. Comprehensive experiments on three standard benchmarks show that, in the ONE-shot setting, our Group-On approach significantly outperforms previous works by considerable margins. For example, on the COCO-20i dataset, we increase mIoU scores by 8.21% and 7.46% on ASNet and HSNet baselines, respectively. With only one support image, Group-On can be even competitive with the counterparts using 5 annotated support images.
Related papers
Err
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.