MedICap: A Concise Model for Medical Image Captioning

MedICap is a medical image captioning encoder-to-decoder model that placed first in the ImageCLEFmedical Caption 2023 challenge: https://www.imageclef.org/2023/medical/caption (team CSIRO).

Paper:

https://ceur-ws.org/Vol-3497/paper-132.pdf

GitHub Repository:

https://github.com/aehrc/imageclefmedical_caption_23

Notebook Example:

https://github.com/aehrc/imageclefmedical_caption_23/blob/main/example.ipynb

Downloads last month: 196

Safetensors

Model size

113M params

Tensor type

F32

Inference Providers NEW

Feature Extraction

This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API does not yet support model repos that contain custom code.

Collection including aehrc/medicap

medicap

Collection

1 item • Updated Dec 12, 2024