CLIFF: Continual Learning for Incremental Flake Features in 2D Material Identification

Sankalp Pandey, Xuan Bac Nguyen, Nicholas Borys, Hugh Churchill, Khoa Luu

Keywords: Computer Vision, Continual Learning, Materials Science

TL;DR: We propose CLIFF, a continual learning framework for 2D material layer count classification that retains knowledge of previously trained materials while sequentially learning new ones through the use of correction modules.

Abstract:

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.
In this paper, we propose a new Continual-Learning Framework for Flake Layer Classification (CLIFF). To our knowledge, this is the first systematic study of continual learning in the domain of two-dimensional (2D) materials.
Our method enables the model to differentiate between materials and their physical and optical properties by freezing a backbone and base head 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, we incorporate memory replay with knowledge distillation.
CLIFF achieves competitive accuracy with significantly lower forgetting than naive fine-tuning and a prompt-based baseline.

Submission Track: Findings, Tools & Open Challenges

Submission Category: AI-Guided Design + Automated Material Characterization

Institution Location: Fayetteville, United States of America

AI4Mat Journal Track: Yes

AI4Mat RLSF: Yes

Submission Number: 40