Self-Compensating Learning for Few-Shot Segmentation

Jin Wang, Bingfeng Zhang*, Weifeng Liu*, Baodi Liu, Siyue Yu

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review


Few-shot segmentation (FSS) has witnessed rapid development. Most existing approaches extract prototypes from support images to segment query images. However, the integrity and validity of these support prototypes cannot be guaranteed. To solve the above drawbacks, we propose a self-compensating strategy, aiming to provide query-aware support information, to build more effective matching between support information and query images. Specifically, we design a prototype compensating module to mine useful information from the query prediction, to update original support prototypes as new query-aware support prototypes. Then the updated prototypes are utilized to perform the second matching with query features. In addition, we also compensate the information of original prior masks on the second matching phase, to improve the quality of prior masks. With improved prototype representations and prior knowledge, our approach can directly improve the performance of different approaches with new state-of-the-art performances.

Original languageEnglish
Title of host publication2023 IEEE International Conference on Image Processing, ICIP 2023 - Proceedings
PublisherIEEE Computer Society
Number of pages5
ISBN (Electronic)9781728198354
Publication statusPublished - 2023
Externally publishedYes
Event30th IEEE International Conference on Image Processing, ICIP 2023 - Kuala Lumpur, Malaysia
Duration: 8 Oct 202311 Oct 2023

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880


Conference30th IEEE International Conference on Image Processing, ICIP 2023
CityKuala Lumpur


  • Few-shot segmentation
  • prior mask
  • prototype
  • self-compensation


Dive into the research topics of 'Self-Compensating Learning for Few-Shot Segmentation'. Together they form a unique fingerprint.

Cite this