PROTOTYPE QUEUE LEARNING FOR MULTI-CLASS FEW-SHOT SEMANTIC SEGMENTATION

Zichao Wang, Zhiyu Jiang, Yuan Yuan

科研成果: 书/报告/会议事项章节会议稿件同行评审

5 引用 (Scopus)

摘要

Few-shot semantic segmentation aims to undertake the segmentation task of novel classes with only a few annotated images. However, most existing methods tend to segment the foreground and background in the image, which limits practical application. In this paper, we present a Prototype Queue Network, which performs few-shot segmentation on multi-class in the images by aggregating binary classes into multiple classes. A prototype queue learning module is proposed to achieve multi-class segmentation by mining the relationship among features of different classes with queue and pseudo labels. In addition, a background latent class distribution refinement module is proposed to prevent the latent novel class in the background from being incorrectly predicted, which refines the boundary among different classes. Furthermore, we propose a two-steps segmentation module to optimize the process of extracting feature representation by adding progressive constraints, which can further improve the accuracy of segmentation. Experiments on the UDD and Vaihingen datasets demonstrate that our method achieves state-of-the-art performance.

源语言英语
主期刊名2022 IEEE International Conference on Image Processing, ICIP 2022 - Proceedings
出版商IEEE Computer Society
1721-1725
页数5
ISBN(电子版)9781665496209
DOI
出版状态已出版 - 2022
活动29th IEEE International Conference on Image Processing, ICIP 2022 - Bordeaux, 法国
期限: 16 10月 202219 10月 2022

出版系列

姓名Proceedings - International Conference on Image Processing, ICIP
ISSN(印刷版)1522-4880

会议

会议29th IEEE International Conference on Image Processing, ICIP 2022
国家/地区法国
Bordeaux
时期16/10/2219/10/22

指纹

探究 'PROTOTYPE QUEUE LEARNING FOR MULTI-CLASS FEW-SHOT SEMANTIC SEGMENTATION' 的科研主题。它们共同构成独一无二的指纹。

引用此