Scholarlink

<p>Learning new concepts while preserving the learned knowledge is the goal for learning systems in Class-Incremental Learning (CIL). Previous methods mainly approach CIL from two perspectives: one focuses on preserving the learned knowledge, making the model compatible with previously learned tasks, i.e., backward-compatible; the other considers making the model prepared for learning new tasks, so the model should also be compatible with the future tasks, i.e., forward-compatible. In this paper, we systematically identify one of the fundamental challenges behind CIL, named <i>feature collision</i>, where the features learned by the current task-specific model may collide with those of the previous models, leading to forgetting of previously learned tasks and hindering the learning of new tasks. Therefore, we propose a bi-compatible CIL framework to promote continual learning by addressing feature collision in both forward and backward compatible manners. Specifically, we consider: 1) forward-compatible task-agnostic feature learning to capture task-agnostic features continually with a separate model in advance for subsequent tasks; 2) backward-compatible rehearsal feature augmentation to preserve the discrimination ability of the learned task-specific feature. The framework is called <i>Bi-compatible Task-agnostic Feature Expansion and Augmentation</i> (BitFea), comprising both forward-compatible feature expansion and backward-compatible feature augmentation. Firstly, it captures task-agnostic features continually with a separate model, providing extra task-agnostic features for subsequent tasks. Secondly, to obtain useful features from the task-agnostic model for the current task, it aggregates the task-agnostic features with the task-specific feature using a merge attention. Then the aggregated feature is transferred back into the task-specific feature for inference, helping the task-specific model capture diverse features. Lastly, the task-specific feature of the rehearsal samples is augmented by a gradient ascent step to help keeping the generalization on the previous tasks, preserving the discrimination ability of the task-specific feature across the learned tasks. Extensive experiments show the effectiveness and superiority of BitFea on various CIL settings. The code is available at <a href="https://github.com/bwnzheng/BitFea_IJCV">https://github.com/bwnzheng/BitFea_IJCV</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Bi-Compatible Task-Agnostic Feature Augmentation for Expansion-Based Class-Incremental Learning

  • 期刊论文

  • 发表日期：

    2026年7月26日

查看全文
  • Bowen Zheng,
  • Zijun Shen,
  • Da-Wei Zhou,
  • Han-Jia Ye,
  • De-Chuan Zhan

摘要

Learning new concepts while preserving the learned knowledge is the goal for learning systems in Class-Incremental Learning (CIL). Previous methods mainly approach CIL from two perspectives: one focuses on preserving the learned knowledge, making the model compatible with previously learned tasks, i.e., backward-compatible; the other considers making the model prepared for learning new tasks, so the model should also be compatible with the future tasks, i.e., forward-compatible. In this paper, we systematically identify one of the fundamental challenges behind CIL, named feature collision, where the features learned by the current task-specific model may collide with those of the previous models, leading to forgetting of previously learned tasks and hindering the learning of new tasks. Therefore, we propose a bi-compatible CIL framework to promote continual learning by addressing feature collision in both forward and backward compatible manners. Specifically, we consider: 1) forward-compatible task-agnostic feature learning to capture task-agnostic features continually with a separate model in advance for subsequent tasks; 2) backward-compatible rehearsal feature augmentation to preserve the discrimination ability of the learned task-specific feature. The framework is called Bi-compatible Task-agnostic Feature Expansion and Augmentation (BitFea), comprising both forward-compatible feature expansion and backward-compatible feature augmentation. Firstly, it captures task-agnostic features continually with a separate model, providing extra task-agnostic features for subsequent tasks. Secondly, to obtain useful features from the task-agnostic model for the current task, it aggregates the task-agnostic features with the task-specific feature using a merge attention. Then the aggregated feature is transferred back into the task-specific feature for inference, helping the task-specific model capture diverse features. Lastly, the task-specific feature of the rehearsal samples is augmented by a gradient ascent step to help keeping the generalization on the previous tasks, preserving the discrimination ability of the task-specific feature across the learned tasks. Extensive experiments show the effectiveness and superiority of BitFea on various CIL settings. The code is available at https://github.com/bwnzheng/BitFea_IJCV.