ReFocus

This repo contains the model for the paper "ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding"

🌐 Homepage |📑 Paper | 🔗 Code

Introduction

ReFocus Finetuning

We follow the Phi-3 Cookbook for the supervised finetuning experiments.

Inference with the Finetuned Model

We release our best finetuned ReFocus model with full chain-of-thought data in this HuggingFace Link.

This model is finetuned based on Phi-3.5-vision, and we used the following prompt during evaluation

<|image|>\n{question}\nThought:

To enforce the model to generate bounding box coordinates to refocus, you could try this prompt:

<|image_1|>\n{question}\nThought: The areas to focus on in the image have bounding box coordinates:

---

license: apache-2.0