JOURNAL ARTICLE

INCPrompt: Task-Aware Incremental Prompting for Rehearsal-Free Class-Incremental Learning

Abstract

This paper introduces INCPrompt, an innovative continual learning solution that effectively addresses catastrophic forgetting. INCPrompt's key innovation lies in its use of adaptive key-learner and task-aware prompts that capture task-relevant information. This unique combination encapsulates general knowledge across tasks and encodes task-specific knowledge. Our comprehensive evaluation across multiple continual learning benchmarks demonstrates INCPrompt's superiority over existing algorithms, showing its effectiveness in mitigating catastrophic forgetting while maintaining high performance. These results highlight the significant impact of task-aware incremental prompting on continual learning performance.

Keywords:
Forgetting Computer science Task (project management) Incremental learning Key (lock) Class (philosophy) Task analysis Artificial intelligence Human–computer interaction Cognitive psychology Engineering Psychology

Metrics

3
Cited By
1.92
FWCI (Field Weighted Citation Impact)
21
Refs
0.81
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Citation History

Topics

Domain Adaptation and Few-Shot Learning
Physical Sciences →  Computer Science →  Artificial Intelligence
Multimodal Machine Learning Applications
Physical Sciences →  Computer Science →  Computer Vision and Pattern Recognition
Human Pose and Action Recognition
Physical Sciences →  Computer Science →  Computer Vision and Pattern Recognition
© 2026 ScienceGate Book Chapters — All rights reserved.