用能量距离提示框架提升模型跨域学习能力，减少遗忘。
HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning
- 结合能量与距离信息，动态优化新旧领域间表示分离度。
- 在CORe50上对未知领域准确率提升2.57%，显著缓解灾难性遗忘。
- 适合需要持续学习新数据领域的实际应用，如智能监控系统。
领域增量学习要求模型在不重新训练的前提下持续适应新数据领域，但领域漂移常导致性能大幅下降。为此，我们提出混合能量-距离提示框架（HEDP），受亥姆霍兹自由能启发。HEDP引入能量正则化损失以增强领域表征的可分性，并设计一种融合能量与距离线索的加权机制，提升领域选择与泛化能力。在多个基准测试（包括CORe50）上的实验表明，该方法在未见领域上实现2.57%的准确率提升，有效缓解灾难性遗忘，增强开放世界适应性。代码已开源。
原文摘要 · Abstract (English)
Domain Incremental Learning is a critical scenario that requires models to continuously adapt to new data domains without retraining. However, domain shifts often cause severe performance degradation. To address this, we propose Hybrid Energy-Distance Prompt, a domain-incremental framework inspired by Helmholtz free energy. HEDP introduces an energy regularization loss to enhance the separability of domain representations and a hybrid energy-distance weighted mechanism that fuses energy-based and distance-based cues to improve domain selection and generalization. Experiments on multiple benchmarks, including CORe50, show that HEDP achieves superior performance on unseen domains with a 2.57\% accuracy gain, effectively mitigating catastrophic forgetting and enhancing open-world adaptability. Our code is \href{https://github.com/dannis97500/HEDP/}{available here}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。