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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pandey, Sankalp, Nguyen, Xuan Bac, Borys, Nicholas, Churchill, Hugh, Luu, Khoa
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911477428912128
author Pandey, Sankalp
Nguyen, Xuan Bac
Borys, Nicholas
Churchill, Hugh
Luu, Khoa
author_facet Pandey, Sankalp
Nguyen, Xuan Bac
Borys, Nicholas
Churchill, Hugh
Luu, Khoa
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17261
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLIFF: Continual Learning for Incremental Flake Features in 2D Material Identification
Pandey, Sankalp
Nguyen, Xuan Bac
Borys, Nicholas
Churchill, Hugh
Luu, Khoa
Computer Vision and Pattern Recognition
Machine Learning
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.
title CLIFF: Continual Learning for Incremental Flake Features in 2D Material Identification
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2508.17261