新框架让模型持续学习识别二维材料层数，遗忘少、准确率高。
CLIFF: Continual Learning for Incremental Flake Features in 2D Material Identification
- 冻结主干网络，为每种新材料学习专属提示与修正头。
- 在3种材料上测试，错误率比微调低40%以上，遗忘显著减少。
- 适合需要持续新增材料的量子器件自动化检测场景。
识别量子晶片对可扩展量子硬件至关重要，但因不同材料在光学显微镜下外观差异大，自动层分类仍具挑战。本文提出首个系统性研究二维材料持续学习的框架——CLIFF。通过冻结参考材料训练的主干和基础头部，针对每种新材料学习特定提示、嵌入和增量头部。采用提示池与余弦相似度门控机制调节特征并计算材料特异性修正。同时引入带知识蒸馏的记忆重放策略。在3种材料上的实验表明，该方法在保持高准确率的同时，显著降低遗忘，相比直接微调和基于提示的基线，错误率下降超40%。
原文摘要 · Abstract (English)
Identifying quantum flakes is crucial for scalable quantum hardware; however, automated layer classification from optical microscopy remains challenging due to substantial appearance shifts across different materials. This paper proposes a new Continual-Learning Framework for Flake Layer Classification (CLIFF). To the best of our knowledge, this work represents the first systematic study of continual learning in two-dimensional (2D) materials. The proposed framework enables the model to distinguish materials and their physical and optical properties by freezing the backbone and base head, which are trained on a reference material. For each new material, it learns a material-specific prompt, embedding, and a delta head. A prompt pool and a cosine-similarity gate modulate features and compute material-specific corrections. Additionally, memory replay with knowledge distillation is incorporated. CLIFF achieves competitive accuracy with significantly lower forgetting than naive fine-tuning and a prompt-based baseline.
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。