---
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
---

This model is trained to classify app introduction images into three categories: `Surrounded Screenshot`, `Screenshot`, and `Irrelevant`.

Code and dataset can be found at https://github.com/Jl-wei/guing

Using with pipeline
```py
from PIL import Image
from transformers import pipeline

classifier = pipeline("image-classification", model="Jl-wei/app-intro-img-classifier", device=0)
image = Image.open(img_path)
result = classifier(image)
```

This is the app introduction image classifier of the following paper:
```bibtex
@article{wei2024guing,
      author = {Wei, Jialiang and Courbis, Anne-Lise and Lambolais, Thomas and Xu, Binbin and Bernard, Pierre Louis and Dray, G\'{e}rard and Maalej, Walid},
      title = {GUing: A Mobile GUI Search Engine using a Vision-Language Model},
      year = {2025},
      volume = {34},
      number = {4},
      doi = {10.1145/3702993},
      journal = {ACM Trans. Softw. Eng. Methodol.},
      publisher = {Association for Computing Machinery},
      address = {New York, NY, USA}
}
```
Please note that the model can only be used for academic purpose.