Seg Zero 7B Best On ReasonSegTest

🚀 Seg-Zero-7B

This model is based on a decoupled architecture with a reasoning model and a segmentation model, enabling robust zero - shot generalization and emergent test - time reasoning.

🚀 Quick Start

This Seg-Zero-7B model is based on the paper Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement. It uses a decoupled architecture with a reasoning model and a segmentation model. Trained via reinforcement learning using GRPO without explicit reasoning data, it achieves robust zero-shot generalization and emergent test-time reasoning.

Code: https://github.com/dvlab-research/Seg-Zero

✨ Features

This model introduces a decoupled architecture. The reasoning model interprets user intentions, generates explicit reasoning chains, and produces positional prompts. The segmentation model then uses these prompts to generate pixel-level masks.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# load model
model = AutoModelForCausalLM.from_pretrained("Ricky06662/Seg-Zero-7B")
tokenizer = AutoTokenizer.from_pretrained("Ricky06662/Seg-Zero-7B")

📚 Documentation

The model has the following properties:

📄 License

The model uses an "other" license.