液晶与显示2026，Vol.41Issue(4)：565-577,13.DOI:10.37188/CJLCD.2026-0050
基于原型对齐的持续图像分割
Continual image segmentation based on prototype alignment
摘要
Abstract
Continual image segmentation suffers from catastrophic forgetting of previously learned classes,insufficient representation of newly introduced classes,and dynamic background semantic shifts in continual image segmentation.To address these issues,this paper proposes PAIS(Prototype-Aligned Incremental Segmentation),a prototype-aligned incremental segmentation method for continual image segmentation.From the perspective of object-level representation stability,PAIS jointly models the initialization,evolution,and historical semantic compensation of decoder object queries during continual learning.Specifically,prototype-aware initialization(PAI)selects semantically salient positions from the current feature map to initialize object queries,thereby improving the modeling capability for new classes.Temporal consistency learning(TCL)constrains the consistency of key semantic positions and their response distributions across adjacent learning stages,which alleviates objectness degradation caused by feature drift.In addition,category-aware memory(CAM)maintains compact class-level memory representations to enhance old-class retention without relying on large-scale image replay.Experiments on continual panoptic segmentation and continual semantic segmentation on the ADE20K dataset demonstrate that the proposed method consistently outperforms representative methods such as ECLIPSE,BalConpas,and CoMFormer under multiple task settings,data splits,and input sequences.Under the setting covering 150 classes,the proposed method achieves a clear improvement in PQ while reducing storage requirements by approximately 10 times.These results show that PAIS provides a favorable balance among new-class adaptation,old-class retention,and memory efficiency.关键词
持续图像分割/原型对齐/时序一致性学习/类别感知记忆/全景分割Key words
continual image segmentation/prototype alignment/temporal consistency learning/category-aware memory/panoptic segmentation分类
信息技术与安全科学引用本文复制引用
高勇占,黄凌霄,姚新波,周开元,徐海喆..基于原型对齐的持续图像分割[J].液晶与显示,2026,41(4):565-577,13.基金项目
国家自然科学基金(No.12462027) （No.12462027）
宁夏自然科学基金(No.2025AAC030205)Supported by National Natural Science Foundation of China(No.12462027) （No.2025AAC030205）
Natural Science Foundation of Ningxia(No.2025AAC030205) （No.2025AAC030205）
