跳到主要导航 跳到搜索 跳到主要内容

CKAA: Cross-Subspace Knowledge Alignment and Aggregation for Robust Continual Learning

  • Lingfeng He
  • , De Cheng
  • , Zhiheng Ma
  • , Huaijie Wang
  • , Dingwen Zhang
  • , Nannan Wang
  • , Xinbo Gao
  • Xidian University
  • Shenzhen University of Advanced Technology

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

Continual Learning (CL) empowers AI models to continuously learn from sequential task streams. Recently, parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance. They typically allocate a unique sub-module for learning each task, with a task recognizer to select the appropriate sub-modules for testing images. However, due to the feature subspace misalignment from independently trained sub-modules, these methods tend to produce ambiguous decisions under misleading task-ids. To address this, we propose Cross-subspace Knowledge Alignment and Aggregation (CKAA), a novel framework that enhances model robustness against misleading task-ids through two key innovations: 1) Dual-level Knowledge Alignment (DKA): By aligning intra-class feature distributions across different subspaces and learning a robust global classifier through a feature simulation process, DKA enables the model to distinguish features from both correct and incorrect subspaces during training. 2) Task-Confidence-guided Mixture of Adapters (TC-MoA): A robust inference scheme that adaptively aggregates task-specific knowledge from relevant sub-modules based on task-confidence scores, avoiding overconfidence in misleading task-id predictions. Extensive experiments demonstrate that CKAA outperforms existing PEFT-based CL methods. Code is available at https://github.com/HHHLF/CKAA_for_CIL

源语言英语
页(从-至)9865-9880
页数16
期刊IEEE Transactions on Image Processing
卷35
DOI
出版状态已出版 - 2026

学术指纹

探究 'CKAA: Cross-Subspace Knowledge Alignment and Aggregation for Robust Continual Learning' 的科研主题。它们共同构成独一无二的学术指纹。

引用此