无需记忆回放，用双层概念原型实现持续学习
DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype
- 为每类构建粗粒度与细粒度概念原型
- 在三个数据集上显著优于现有无回放方法
- 适合资源受限的实时视觉系统
领域增量学习（DIL）使视觉模型能在真实环境中适应动态变化，同时保留过往知识。由于隐私和训练时间限制，无回放增量学习（RFDIL）更具实用性。受人类认知过程启发，我们为每类设计双层概念原型（DualCP），以解决学习新知识与保留旧知识之间的冲突。通过提出概念原型生成器（CPG），为每类生成粗粒度和细粒度原型，并引入粗到细校准器（C2F）对齐图像特征与双层原型。最后，设计双点回归损失（DDR）优化C2F模块。在DomainNet、CDDB和CORe50数据集上的大量实验表明该方法有效。
原文摘要 · Abstract (English)
Domain-Incremental Learning (DIL) enables vision models to adapt to changing conditions in real-world environments while maintaining the knowledge acquired from previous domains. Given privacy concerns and training time, Rehearsal-Free DIL (RFDIL) is more practical. Inspired by the incremental cognitive process of the human brain, we design Dual-level Concept Prototypes (DualCP) for each class to address the conflict between learning new knowledge and retaining old knowledge in RFDIL. To construct DualCP, we propose a Concept Prototype Generator (CPG) that generates both coarse-grained and fine-grained prototypes for each class. Additionally, we introduce a Coarse-to-Fine calibrator (C2F) to align image features with DualCP. Finally, we propose a Dual Dot-Regression (DDR) loss function to optimize our C2F module. Extensive experiments on the DomainNet, CDDB, and CORe50 datasets demonstrate the effectiveness of our method.
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。