Kingma, D.P. and Welling, M. (2013) Auto-Encoding Variational Bayes.
https://doi.org/10.48550/arXiv.1312.6114

has been cited by the following article:

• TITLE: Study of Methods for Automatic Segmentation of Geological Profile Images Based on Diffusion Models

  AUTHORS: Mengchao Zhao, Zhonghua Ma

  KEYWORDS: Large Models, Fine-Tuning, Geological Image Segmentation

  JOURNAL NAME: Journal of Computer and Communications, Vol.13 No.10, October 24, 2025

  ABSTRACT: Large models perform better than traditional deep learning methods in terms of generalization and continuous learning capabilities, but the application of large models in vertical fields still needs to be developed. This study attempts to apply large models to the field of geological image segmentation, based on the Stable Diffusion model. By fine-tuning a small number of samples in geological image aspects of the model, combined with prompt word engineering, the model realizes automatic division of geological profile images. Experimental results show that large models can achieve vertical domain tasks downstream with small sample fine-tuning and prompt word engineering.