mlsanityData to 14 Oct 2026

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

arXiv 2508.17261 ↗First posted 24 Aug 2025cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 33 of its 51 references that are in the map. First posted on arXiv 24 Aug 2025.

Builds on

33 of 51 references.

References · 33

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2023Segment Anythingcited by 8,234
  4. 2017Mask R-CNNcited by 7,277
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  7. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  8. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  9. 2018Efficient Lifelong Learning with A-GEMcited by 1,058
  10. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 911
  11. 2019Large Scale Incremental Learningcited by 732
  12. 2019Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgettingcited by 302
21 more
  1. 2021Co2L: Contrastive Continual Learningcited by 244
  2. 2020Using Hindsight to Anchor Past Knowledge in Continual Learningcited by 161
  3. 2018Memory Efficient Experience Replay for Streaming Learningcited by 128
  4. 2021Continual Learning of a Mixed Sequence of Similar and Dissimilar Taskscited by 81
  5. 2021BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentationcited by 31
  6. 2023FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understandingcited by 27
  7. 2019Deep-Learning-Based Image Segmentation Integrated with Optical Microscopy for Automatically Searching for Two-Dimensional Materialscited by 17
  8. 2023Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environmentscited by 16
  9. 2022Two-Dimensional Quantum Material Identification via Self-Attention and Soft-labeling in Deep Learningcited by 15
  10. 2023Quantum Vision Clusteringcited by 13
  11. 2023FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understandingcited by 13
  12. 2022OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptationcited by 12
  13. 2022Self-supervised Domain Adaptation in Crowd Countingcited by 11
  14. 2022CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Carscited by 11
  15. 2024Quantum Visual Feature Encoding Revisitedcited by 10
  16. 2024Diffusion-Inspired Quantum Noise Mitigation in Parameterized Quantum Circuitscited by 10
  17. 2019Defining Quantum Neural Networks via Quantum Time Evolutioncited by 8
  18. 2024Hierarchical Quantum Control Gates for Functional MRI Understandingcited by 8
  19. 2025QMoE: A Quantum Mixture of Experts Framework for Scalable Quantum Neural Networkscited by 7
  20. 2024COBRA: A Continual Learning Approach to Vision-Brain Understandingcited by 4
  21. 2023CoMaL: Conditional Maximum Likelihood Approach to Self-supervised Domain Adaptation in Long-tail Semantic Segmentationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026OpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum Materialscited by 1
  2. 2026QuPAINT: Physics-Aware Multimodal Reasoning for Quantum Material Characterizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026QuPAINT: Physics-Aware Instruction Tuning Approach to Quantum Material Discovery
  2. 2026Towards Automated Discovery: A Review of Generative Models, Multimodal Learning and Closed-Loop Workflows in Inverse Materials Design
  3. 2026Composable Crystals: Controllable Materials Discovery via Concept Learning
  4. 2026MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Science
  5. 2025Curiosity Driven Exploration to Optimize Structure-Property Learning in Microscopy
  6. 2024Preliminary Investigations of a Multi-Faceted Robust and Synergistic Approach in Semiconductor Electron Micrograph Analysis: Integrating Vision Transformers with Large Language and Multimodal Models
  7. 2026C2NP: A Benchmark for Learning Scale-Dependent Geometric Invariances in 3D Materials Generation
  8. 2026Optimizing Expert-Designed Crystal Graph Networks for Band-Gap Prediction with an Autonomous LLM Research Loop