TY  - CONF
AU  - Kazimi, Bashir
AU  - Sandfeld, Stefan
TI  - Comparative Analysis of Self-Supervised Learning Techniques for Electron Microscopy Images
VL  - 129
SN  - 2117-4458
CY  - Les Ulis
PB  - EDP Sciences
M1  - FZJ-2025-02590
T2  - BIO Web of Conferences
SP  - 10037 -
PY  - 2024
AB  - Deep learning has revolutionized a wide array of tasks across differentdomains, including electron microscopy (EM) image analysis, by leveraginglarge labeled datasets for training. However, the scarcity of such labeleddatasets in EM necessitates the exploration of alternative methods. Self-supervised learning (SSL) emerges as a promising approach to leverageunlabeled data, featuring techniques such as, e.g., masked image modeling(MIM) — which predicts missing parts of the input data, as well as contrastivelearning — which learns by distinguishing between similar and dissimilar pairsof data. This study aims to investigate the impact of these SSL techniques onEM images, providing a case study on the effectiveness of leveragingunlabeled data in a domain where labeled datasets are limited and expensiveto create.
T2  - The 17th European Microscopy Congress 2024
CY  - 25 Aug 2024 - 30 Aug 2024, Copenhagen (Denmark)
Y2  - 25 Aug 2024 - 30 Aug 2024
M2  - Copenhagen, Denmark
LB  - PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
DO  - DOI:10.1051/bioconf/202412910037
UR  - https://juser.fz-juelich.de/record/1042604
ER  -