Enhance model card for Label Anything with metadata, links, abstract, and usage

README.md

@@ -1,12 +1,102 @@
 ---
+license: mit
+pipeline_tag: image-segmentation
 tags:
 - model_hub_mixin
 - pytorch_model_hub_mixin
 ---
 
-This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
-- Code: [More Information Needed]
-- ArXiv: https://arxiv.org/abs/2407.02075
-- Docs: [More Information Needed]
+# 🏷️ [Label Anything](https://pasqualedem.github.io/LabelAnything/)
 
-run: zm6ws2k9
+### Multi-Class Few-Shot Semantic Segmentation with Visual Prompts
+
+[![Project Page](https://img.shields.io/badge/🌐_Project-Page-blue.svg)](https://pasqualedem.github.io/LabelAnything/)
+[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/label-anything-multi-class-few-shot-semantic/few-shot-semantic-segmentation-on-coco-20i-2-1)](https://paperswithcode.com/sota/few-shot-semantic-segmentation-on-coco-20i-2-1?p=label-anything-multi-class-few-shot-semantic)
+[![arXiv](https://img.shields.io/badge/arXiv-2407.02075-b31b1b.svg)](https://arxiv.org/abs/2407.02075)
+[![ECAI 2025](https://img.shields.io/badge/ECAI-2025-brightgreen.svg)](https://ecai2025.org/)
+[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/pasqualedem/LabelAnything/blob/main/LICENSE)
+
+## 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.
+
+The model was presented in the paper [Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts](https://huggingface.co/papers/2407.02075).
+
+### 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. Code and trained models are available at this https URL .
+
+<div align="center">
+
+![Label Anything Demo](https://github.com/pasqualedem/LabelAnything/raw/main/assets/la.png)
+
+*Visual prompting meets few-shot learning with a new fast and efficient architecture.*
+
+</div>
+
+## Links
+
+*   **Paper on Hugging Face:** [https://huggingface.co/papers/2407.02075](https://huggingface.co/papers/2407.02075)
+*   **Project Page:** [https://pasqualedem.github.io/LabelAnything/](https://pasqualedem.github.io/LabelAnything/)
+*   **GitHub Repository:** [https://github.com/pasqualedem/LabelAnything](https://github.com/pasqualedem/LabelAnything)
+
+## 🚀 Quick Start
+
+### ⚡ 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.
+
+### 🛠️ Manual Installation
+
+For development and customization:
+
+```bash
+# Clone the repository
+git clone https://github.com/pasqualedem/LabelAnything.git
+cd LabelAnything
+
+# Create virtual environment with uv
+uv sync
+source .venv/bin/activate
+```
+
+> **⚠️ System Requirements**: Linux environment with CUDA 12.1 support
+
+### 🔌 Model Loading
+
+```python
+from label_anything.models import LabelAnything
+
+# Load pre-trained model
+model = LabelAnything.from_pretrained("pasqualedem/label_anything_sam_1024_coco")
+```
+
+## 📦 Pre-trained Models
+
+Access our collection of state-of-the-art checkpoints:
+
+| 🧠 Encoder | 📐 Embedding Size | 🖼️ Image Size | 📁 Fold | 🔗 Checkpoint |
+|------------|-------------------|----------------|----------|---------------|
+| **SAM** | 512 | 1024 | - | [![HF](https://img.shields.io/badge/%F0%9F%A4%97_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/%F0%9F%A4%97_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/%F0%9F%A4%97_HuggingFace-Model-FFD21E?style=for-the-badge)](https://huggingface.co/pasqualedem/label_anything_coco_fold0_mae_7a5p0t63) |
+
+## 📄 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}
+}
+```