轻量级增量学习模型，快速适应新类别且不重训主干网络。
HydraCIL: Decoupled Class-Incremental Learning through Prototype-Guided Multi-Head Classifiers
- 用原型引导的多头分类器解耦特征提取与学习过程。
- 在多个数据集上性能媲美或超越主流方法，训练时间大幅缩短。
- 适合资源受限的嵌入式设备，如机器人和边缘AI终端使用。
我们提出HydraCIL，一种基于原型引导多头分类器的解耦式持续学习模型，旨在实现嵌入式和资源受限环境下的可持续部署。现有类增量学习（CIL）方法通常依赖高性能硬件和长时间重训练，而真实系统如机器人或边缘AI设备需在有限资源下快速适应。HydraCIL通过冻结主干网络，将特征提取与学习过程解耦：每个任务仅需一次特征提取，并生成轻量级、任务专属的分类头，避免昂贵的主干重训练。推理时，通过与原型的相似性选择合适分类头。在CIFAR-100、ImageNet-100、CoRe50和Flowers102上的实验表明，HydraCIL在性能上达到或超过当前最优方法，同时显著降低训练时间和碳足迹，为能源效率与快速适应至关重要的实际场景提供可行方案。
原文摘要 · Abstract (English)
We present HydraCIL, a decoupled continual learning model based on prototype-guided multi-head classifiers, targeting sustainable deployment in embedded and resource-constrained environments. While most Class-Incremental Learning (CIL) methods rely on powerful hardware and long retraining cycles, real-world systems, such as robots or edge AI devices, must adapt quickly with limited resources. HydraCIL addresses this gap by freezing the backbone and decoupling feature extraction from learning. For each task, features are extracted once and a lightweight, task-specific classifier head is created, avoiding costly backbone retraining. At inference, HydraCIL selects the appropriate head via similarity with prototypes. Experiments on CIFAR-100, ImageNet-100, CoRe50, and Flowers102 datasets show that HydraCIL matches or outperforms state-of-the-art CIL methods while significantly reducing training time and carbon footprint, making it a practical solution for continual learning in real-world and embedded settings, where energy efficiency and rapid adaptation are critical.
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。