0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Sign in to save

Zero-shot learning for holographic context analysis in microplastics probing

Digital Holography and 3-D Imaging 2022 2022
Yanmin Zhu, Hau Kwan Abby Lo, Chok Hang Yeung, Edmund Y. Lam

Summary

Researchers developed a zero-shot machine learning method using attribute embedding for holographic image analysis to identify unknown microplastic types without requiring labelled training data for every class. The approach reduces the need for manual dataset annotation and improves practical deployment of microplastic detection systems.

A zero-shot learning method with attribute embedding is developed for holographic image analysis and microplastics probing. Experimental results show its efficacy in identifying the unknown microplastics and alleviating the need for manual dataset class annotation.

Share this paper