paper-with-me

홈 › Papers

Segment Anything Model for Grain Characterization in Hard Drive Design

2024-08-22 · Kai Nichols, Matthew Hauwiller, Nicholas Propes, Shaowei Wu, Stephanie Hernandez, Mike Kautzky

Development of new materials in hard drive designs requires characterization of nanoscale materials through grain segmentation. The high-throughput quickly changing research environment makes zero-shot generalization an incredibly desirable feature. For this reason, we explore the application of Meta's Segment Anything Model (SAM) to this problem. We first analyze the out-of-the-box use of SAM. Then we discuss opportunities and strategies for improvement under the assumption of minimal labeled data availability. Out-of-the-box SAM shows promising accuracy at property distribution extraction. We are able to identify four potential areas for improvement and show preliminary gains in two of the four areas.

📄 PDF Abstract BibTeX arXiv:2408.12732

Code (0)

등록된 구현이 없습니다.

Tasks

Zero-shot Generalization

Methods 이 논문이 사용한 방법론

SAM 설명 없음

Similar Papers 제목 키워드 기반

Zero-shot Autonomous Microscopy for Scalable and Intelligent Characterization of 2D Materials

2025-04-14 · Jingyun Yang, Ruoyan Avery Yin, Chi Jiang, Yuepeng Hu 외

Characterization of atomic-scale materials traditionally requires human experts with months to years of specialized training. Even for trained human operators, accurate and reliable characterization remains challenging w…

Image SegmentationPrompt EngineeringSemantic Segmentation

MatSAM: Efficient Extraction of Microstructures of Materials via Visual Large Model

2024-01-11 · Changtai Li, Xu Han, Chao Yao, Xiaojuan Ban

Efficient and accurate extraction of microstructures in micrographs of materials is essential in process optimization and the exploration of structure-property relationships. Deep learning-based image segmentation techni…

Image SegmentationPrompt EngineeringSegmentationSemantic Segmentation+2

SAMBA: A Trainable Segmentation Web-App with Smart Labelling

2023-12-07 · Ronan Docherty, Isaac Squires, Antonis Vamvakeros, Samuel J. Cooper

Segmentation is the assigning of a semantic class to every pixel in an image and is a prerequisite for various statistical analysis tasks in materials science, like phase quantification, physics simulations or morphologi…

Interactive SegmentationSegmentation

Evaluation Study on SAM 2 for Class-agnostic Instance-level Segmentation

2024-09-04 · Jialun Pei, Zhangjun Zhou, Tiantian Zhang

Segment Anything Model (SAM) has demonstrated powerful zero-shot segmentation performance in natural scenes. The recently released Segment Anything Model 2 (SAM2) has further heightened researchers' expectations towards …

Dichotomous Image SegmentationImage SegmentationInstance SegmentationSegmentation+2

LENS: Learning to Segment Anything with Unified Reinforced Reasoning

2025-08-19 · Lianghui Zhu, Bin Ouyang, Yuxuan Zhang, Tianheng Cheng 외 arxiv

Text-prompted image segmentation enables fine-grained visual understanding and is critical for applications such as human-computer interaction and robotics. However, existing supervised fine-tuning methods typically igno…

Image Segmentation