Ruggero1912/Patch-ioner_talk2dino_viecap_COCO_Captions

Patch-ionertalk2dinoviecapCOCOCaptions - Patch-ioner Configuration

This repository contains a pre-trained VIECAP model from the Patch-ioner framework for dense image captioning and controllable visual description.

📝 Paper Information

Title: "One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework" Authors: Lorenzo Bianchi, Giacomo Pacini, Fabio Carrara, Nicola Messina, Giuseppe Amato, Fabrizio Falchi ArXiv: https://arxiv.org/abs/2510.02898 Project Page: https://paciosoft.com/Patch-ioner/

💻 GitHub Repository

The official code repository for Patch-ioner can be found here: https://github.com/Ruggero1912/Patch-ioner

🎯 Model Overview

• —Model Type: VIECAP
• —Configuration: mlp.viecap.k.yaml
• —Vision Backbone: dinov2vitb14reg
• —Language Model: gpt2
• —Input Resolution: 518x518
• —Prefix Size: 768

VieCap Configuration

• —Continuous Prompt Length: 10
• —Clip Project Length: 10
• —Temperature: 0.01
• —Top-K: 3
• —Entity Retrieval: coco_entities

📊 Performance

📈 Detailed Results

Image Captioning Results

• —METEOR: 0.2250
• —CIDEr: 0.7690
• —SPICE: 0.1612
• —BLEU_4: 0.2362
• —ROUGE_L: 0.4779
• —CLIP-S: 0.7188

Narratives Results

• —METEOR: 10.7000
• —CIDEr: 28.2000
• —SPICE: 12.5000
• —BLEU_4: 2.6000
• —ROUGE_L: 23.1000
• —CLIP-S: 66.5000

🚀 Quick Start

from patch_ioner import load_model, Patchioner

# Load the model
config_path = "config.yaml"
model = load_model(config_path)

# Run inference
image_path = "your_image.jpg"
results = model.forward(image_path)
print(results)

transformers Sample Usage

The model can also be loaded using the transformers library:

from transformers import AutoModel

MODEL_ID = "Ruggero1912/Patch-ioner_talk2dino_viecap_COCO_Captions" # Note: use the correct MODEL_ID for this repository
model = AutoModel.from_pretrained(MODEL_ID, trust_remote_code=True)

📁 Repository Contents

• —config.yaml: Model configuration file
• —model.pt: Pre-trained model weights
• —README.md: This file

🔧 Installation

pip install git+https://github.com/Ruggero1912/Patch-ioner

💡 Usage Examples

Refer to the Patch-ioner repository for updated usage examples.

🎛️ Model Configuration

• —Prefix Size: 768
• —Memory Bank Size: 0
• —Normalization: False

📈 Training Details

• —Training Dataset: COCO Captions
• —Training Epochs: TBD
• —Batch Size: TBD
• —Learning Rate: TBD
• —Optimizer: AdamW

📚 Citation

If you use this model in your research, please cite our paper, refer to the Project Page for updated citation template.

🤝 Contributing

We welcome contributions to improve the Patch-ioner framework. Please see the main repository for contribution guidelines.

📄 License

See the main repository for detailed license information.

🐛 Issues and Support

For issues related to this model or the Patch-ioner framework, please:

1. 1.Check the main repository for existing issues
2. 2.Open a new issue with detailed information about your problem
3. 3.Contact the authors.

🔗 Related Models

Explore other Patch-ioner model configurations:

• —Patch-ioner_mlp - MLP-based DeCap model
• —Patch-ioner_viecap - VieCap controllable captioning
• —Patch-ioner_clipcap - ClipCap integration

More models available in [Ruggero1912's models](https://huggingface.co/Ruggero1912)

This model is part of the Patch-ioner framework for dense image captioning and controllable visual description.