# ForamViT-GAN: Exploring New Paradigms in Deep Learning for Micropaleontological Image Analysis

arXiv: https://arxiv.org/abs/2304.04291 · HTML: https://mlsanity.com/paper/2304.04291/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 52 references that are in the map.
- First posted on arXiv 9 Apr 2023.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [Repurposing GANs for One-shot Semantic Part Segmentation](https://mlsanity.com/paper/2103.04379/) (2021)
- [Learning from Few Examples: A Summary of Approaches to Few-Shot Learning](https://mlsanity.com/paper/2203.04291/) (2022)
- [Reconstruction of three-dimensional porous media using generative adversarial neural networks](https://mlsanity.com/paper/1704.03225/) (2017)
- [Revisiting RCAN: Improved Training for Image Super-Resolution](https://mlsanity.com/paper/2201.11279/) (2022)
- [More Real than Real: A Study on Human Visual Perception of Synthetic Faces](https://mlsanity.com/paper/2106.07226/) (2021)
- [Classification of volcanic ash particles using a convolutional neural network and probability](https://mlsanity.com/paper/1805.12353/) (2018)
- [Instance Segmentation of Microscopic Foraminifera](https://mlsanity.com/paper/2105.14191/) (2021)
- [Generating unrepresented proportions of geological facies using Generative Adversarial Networks](https://mlsanity.com/paper/2203.09639/) (2022)
- [PetroGAN: A novel GAN-based approach to generate realistic, label-free petrographic datasets](https://mlsanity.com/paper/2204.05114/) (2022)

## Built on by (most cited first, 1 of 1)

- [ForamDeepSlice: A High-Accuracy Deep Learning Framework for Foraminifera Species Classification from 2D Micro-CT Slices](https://mlsanity.com/paper/2512.00912/) (2025)

## Abstract (arXiv)

Micropaleontology in geosciences focuses on studying the evolution of microfossils (e.g., foraminifera) through geological records to reconstruct past environmental and climatic conditions. This field heavily relies on visual recognition of microfossil features, making it suitable for computer vision technology, specifically deep convolutional neural networks (CNNs), to automate and optimize microfossil identification and classification. However, the application of deep learning in micropaleontology is hindered by limited availability of high-quality, high-resolution labeled fossil images and the significant manual labeling effort required by experts. To address these challenges, we propose a novel deep learning workflow combining hierarchical vision transformers with style-based generative adversarial network algorithms to efficiently acquire and synthetically generate realistic high-resolution labeled datasets of micropaleontology in large volumes. Our study shows that this workflow can generate high-resolution images with a high signal-to-noise ratio (39.1 dB) and realistic synthetic images with a Frechet inception distance similarity score of 14.88. Additionally, our workflow provides a large volume of self-labeled datasets for model benchmarking and various downstream visual tasks, including fossil classification and segmentation. For the first time, we performed few-shot semantic segmentation of different foraminifera chambers on both generated and synthetic images with high accuracy. This novel meta-learning approach is only possible with the availability of high-resolution, high-volume labeled datasets. Our deep learning-based workflow shows promise in advancing and optimizing micropaleontological research and other visual-dependent geological analyses.