Improve model card for Label Anything: Add metadata, links, abstract, and usage

README.md

@@ -2,9 +2,96 @@
 tags:
 - model_hub_mixin
 - pytorch_model_hub_mixin
+license: mit
+pipeline_tag: image-segmentation
 ---
 
-This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
-- Library: [More Information Needed]
-- Docs: [More Information Needed]
-- ArXiv: https://arxiv.org/abs/2407.02075
+# 🏷️ Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts
+
+**Label Anything** introduces a novel transformer-based architecture designed for multi-prompt, multi-way few-shot semantic segmentation, significantly reducing annotation burden while maintaining high accuracy.
+
+[![Paper](https://img.shields.io/badge/Paper-2407.02075-b31b1b.svg)](https://huggingface.co/papers/2407.02075)
+[![Project Page](https://img.shields.io/badge/🌐_Project-Page-blue.svg)](https://pasqualedem.github.io/LabelAnything/)
+[![arXiv](https://img.shields.io/badge/arXiv-2407.02075-b31b1b.svg)](https://arxiv.org/abs/2407.02075)
+[![GitHub](https://img.shields.io/badge/GitHub-Code-keygen.svg?logo=github&style=flat-square)](https://github.com/pasqualedem/LabelAnything)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/pasqualedem/LabelAnything/blob/main/LICENSE)
+
+## Abstract
+Few-shot semantic segmentation aims to segment objects from previously unseen classes using only a limited number of labeled examples. In this paper, we introduce Label Anything, a novel transformer-based architecture designed for multi-prompt, multi-way few-shot semantic segmentation. Our approach leverages diverse visual prompts -- points, bounding boxes, and masks -- to create a highly flexible and generalizable framework that significantly reduces annotation burden while maintaining high accuracy. Label Anything makes three key contributions: ($\textit{i}$) we introduce a new task formulation that relaxes conventional few-shot segmentation constraints by supporting various types of prompts, multi-class classification, and enabling multiple prompts within a single image; ($\textit{ii}$) we propose a novel architecture based on transformers and attention mechanisms; and ($\textit{iii}$) we design a versatile training procedure allowing our model to operate seamlessly across different $N$-way $K$-shot and prompt-type configurations with a single trained model. Our extensive experimental evaluation on the widely used COCO-$20^i$ benchmark demonstrates that Label Anything achieves state-of-the-art performance among existing multi-way few-shot segmentation methods, while significantly outperforming leading single-class models when evaluated in multi-class settings.
+
+## Overview
+**Label Anything** is a novel method for multi-class few-shot semantic segmentation using visual prompts. This repository contains the official implementation of our ECAI 2025 paper, enabling precise segmentation with just a few prompted examples.
+
+<div align="center">
+  <img src="https://github.com/pasqualedem/LabelAnything/raw/main/assets/la.png" alt="Label Anything Demo" width="70%">
+  <em>Visual prompting meets few-shot learning with a new fast and efficient architecture.</em>
+</div>
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration.
+
+## ✨ Key Features
+-   **🎯 Few-Shot Learning**: Achieve remarkable results with minimal training data.
+-   **🖼️ Visual Prompting**: Intuitive interaction through visual cues (points, bounding boxes, masks).
+-   **⚡ Multi-GPU Support**: Accelerated training on modern hardware.
+-   **🔄 Cross-Validation**: Robust 4-fold evaluation protocol.
+-   **📊 Rich Logging**: Comprehensive experiment tracking with Weights & Biases.
+-   **🤗 HuggingFace Integration**: Seamless model sharing and deployment.
+
+## 🚀 How to Use
+
+### ⚡ One-Line Demo
+Experience Label Anything instantly with our streamlined demo:
+
+```bash
+uvx --from git+https://github.com/pasqualedem/LabelAnything app
+```
+
+> **💡 Pro Tip**: This command uses [uv](https://docs.astral.sh/uv/) for lightning-fast package management and execution.
+
+### 🔌 Model Loading (Python)
+You can load a pre-trained model as follows:
+
+```python
+from label_anything.models import LabelAnything
+
+# Load pre-trained model, e.g., "pasqualedem/label_anything_sam_1024_coco"
+model = LabelAnything.from_pretrained("pasqualedem/label_anything_sam_1024_coco")
+```
+
+For detailed usage, including manual installation and the training pipeline, please refer to the [official GitHub repository](https://github.com/pasqualedem/LabelAnything).
+
+## 📦 Pre-trained Models
+Access our collection of state-of-the-art checkpoints:
+
+<div align="center">
+
+| 🧠 Encoder | 📐 Embedding Size | 🖼️ Image Size | 📁 Fold | 🔗 Checkpoint |
+|------------|-------------------|----------------|----------|---------------|
+| **SAM** | 512 | 1024 | - | [![HF](https://img.shields.io/badge/🤗_HuggingFace-Model-FFD21E?style=for-the-badge)](https://huggingface.co/pasqualedem/label_anything_sam_1024_coco) |
+| **ViT-MAE** | 256 | 480 | - | [![HF](https://img.shields.io/badge/🤗_HuggingFace-Model-FFD21E?style=for-the-badge)](https://huggingface.co/pasqualedem/label_anything_mae_480_coco) |
+| **ViT-MAE** | 256 | 480 | 0 | [![HF](https://img.shields.io/badge/🤗_HuggingFace-Model-FFD21E?style=for-the-badge)](https://huggingface.co/pasqualedem/label_anything_coco_fold0_mae_7a5p0t63) |
+
+</div>
+
+## 📄 Citation
+If you find Label Anything useful in your research, please cite our work:
+
+```bibtex
+@inproceedings{labelanything2025,
+  title={LabelAnything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts},
+  author={De Marinis, Pasquale and Fanelli, Nicola and Scaringi, Raffaele and Colonna, Emanuele and Fiameni, Giuseppe and Vessio, Gennaro and Castellano, Giovanna},
+  booktitle={ECAI 2025},
+  year={2025}
+}
+```
+
+## 📜 License
+This project is licensed under the MIT License - see the [LICENSE](https://github.com/pasqualedem/LabelAnything/blob/main/LICENSE) file for details.
+
+---
+
+<div align="center">
+
+**Made with ❤️ by the CilabUniba Label Anything Team**
+
+</div>