https://github.com/semanticclimate/image_classification
https://github.com/semanticclimate/image_classification
Last synced: 9 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/semanticclimate/image_classification
- Owner: semanticClimate
- License: apache-2.0
- Created: 2025-08-01T10:27:17.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2025-08-01T10:47:02.000Z (11 months ago)
- Last Synced: 2025-08-01T12:51:01.616Z (11 months ago)
- Language: Jupyter Notebook
- Size: 3.44 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Citation: CITATION.cff
Awesome Lists containing this project
README
# Exploring Vision Transformers in Practice
DOI Zenodo badge:
[](https://doi.org/10.5281/zenodo.16734915)
Citation
Hamadani, A., Kumari, R., Simon, W., Yadav, G., & Murray-Rust, P. (2025). Exploring Vision Transformers in Practice (0.1). Zenodo. https://doi.org/10.5281/zenodo.16734915
Description:
In this notebook, we fine-tune a pretrained ViT on the Fashion Products Small dataset from Hugging Face, which contains 42,700 e-commerce images of apparel and accessories (e.g., shirts, watches) along with metadata. The data is split into training, validation, and testing. Rather than training from scratch, the notebook uses ViT-Base-Patch16-224-in21k from Hugging Face’s Transformers library.
**Vision Transformers in Academic Research**
- Understanding Visual Texts
- Analyzing Literature Reviews
- Multimodal Literature Review
- Sorting Large Collections
- Symbolism Analysis in Art
- Visual Semantic Mapping
[Link to Notebook](https://colab.research.google.com/drive/1K0Dam1Pxi2YtruwcCe1XgwL_pLtBWJHP?usp=sharing)
Reviewers & review process: \
---
Software citation information: [CITATION.cff](CITATION.cff)
License: Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ | License information: [LICENSE](LICENSE)