HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning

TL;DR

HEDP is a novel framework for domain incremental learning that uses energy regularization and hybrid cues to improve domain adaptation and reduce forgetting.

Contribution

It introduces a hybrid energy-distance prompt mechanism inspired by Helmholtz free energy for better domain representation and generalization.

Findings

HEDP achieves a 2.57% accuracy gain on unseen domains.

It effectively mitigates catastrophic forgetting.

It enhances open-world adaptability.

Abstract

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}.