Finding the semantic similarity in single-particle diffraction images using self-supervised contrastive projection learning

查看全文 作　　者：Julian [1]Zimmermann;Fabien [1]Beguet;Daniel [1]Guthruf;Bruno [2]Langbehn;Daniela [1,3]Rupp

机构地区：[1]ETH Zürich,Zürich,Switzerland;[2]Technische Universität Berlin,Berlin,Germany;[3]Max-Born-Institut,Berlin,Germany

出　　处：《npj Computational Materials》索引2023年第1期,共9页

摘　　要：Single-shot coherent diffraction imaging of isolated nanosized particles has seen remarkable success in recent years,yielding in-situ measurements with ultra-high spatial and temporal resolution.The progress of high-repetition-rate sources for intense X-ray pulses has further enabled recording datasets containing millions of diffraction images,which are needed for the structure determination of specimens with greater structural variety and dynamic experiments.The size of the datasets,however,represents a monumental problem for their analysis.Here,we present an automatized approach for finding semantic similarities in coherent diffraction images without relying on human expert labeling.By introducing the concept of projection learning,we extend self-supervised contrastive learning to the context of coherent diffraction imaging and achieve a dimensionality reduction producing semantically meaningful embeddings that align with physical intuition.The method yields substantial improvements compared to previous approaches,paving the way toward real-time and large-scale analysis of coherent diffraction experiments at X-ray free-electron lasers. 关键词：PROJECTION COHERENT SIMILARITY

相关文献

参考文献（88）
引证文献（0）
耦合文献（8）

参考文献(88)

耦合文献(8)

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费

Finding the semantic similarity in single-particle diffraction images using self-supervised contrastive projection learning

参考文献(88)

耦合文献(8)

用户提示