RankSEG is a plug-and-play post-processing module that boosts segmentation performance (Dice/IoU) during inference. It works with ANY pre-trained probabilistic segmentation model (SAM, DeepLab, SegFormer, etc.) without any retraining or fine-tuning.

Explore RankSEG by reading our documentation.

🌟 Why RankSEG?

Conventional methods use argmax or fixed thresholding, which are not theoretically optimized for non-decomposable metrics like Dice or IoU. RankSEG bridges this gap by directly optimizing the target metric, yielding "free" performance gains.

Demo: RankSEG vs. Argmax on fashn-human-parser

⚡ Quick Start

RankSEG is designed to be dropped into your existing inference pipeline with just a few lines of code.

1. Installation

pip install -U rankseg

2. Basic Usage (3 Lines of Code)

from rankseg import RankSEG
import torch.nn.functional as F

# 1. Initialize RankSEG (optimizing for Dice)
rankseg = RankSEG(metric='dice')

# 2. Get probability output from YOUR model
# probs: (Batch, Class, H, W)
probs = F.softmax(model_logits, dim=1)

# 3. Get optimized predictions (Instantly!)
preds = rankseg.predict(probs)

💡 Try it now:

✨ Key Features

• 🚀 Performance Boost: Consistently improves mIoU/mDice scores over standard argmax.
• 🔌 Zero Effort: Compatible with any PyTorch model. No retraining, no fine-tuning.
• 🆓 Training-Free: Purely post-processing. Works with frozen weights.
• ⚡ Real-time Inference: Efficient RMA (Reciprocal Moment Approximation) solver.
• 🧩 Versatile: Supports semantic (multi-class) and binary (multi-label) tasks.

📊 Benchmarks

RankSEG delivers consistent gains across various architectures and datasets without touching a single weight.

Detailed results available in our NeurIPS 2025 paper.

🛠️ Integrations & Demos

Framework	Task	Quick Start
Standard PyTorch	Semantic Segmentation
Segment Anything (SAM)	Zero-shot Segmentation
Hugging Face	Interactive Demo
PaddleSeg

🔗 Citation

If you use RankSEG in your research, please cite our papers:

• Dai, B., & Li, C. (2023). RankSEG: A Consistent Ranking-based Framework for Segmentation. Journal of Machine Learning Research, 24(224), 1-50. [link]
• Wang, Z., & Dai, B. (2025). RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment Approximation. Advances in Neural Information Processing Systems (NeurIPS 2025). [link]

@article{dai2023rankseg,
  title={RankSEG: A Consistent Ranking-based Framework for Segmentation},
  author={Dai, Ben and Li, Chunlin},
  journal={Journal of Machine Learning Research},
  volume={24},
  number={224},
  pages={1--50},
  url={https://www.jmlr.org/papers/v24/22-0712.html},
  year={2023}
}

@inproceedings{wang2025rankseg,
  title={RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment Approximation},
  author={Wang, Zixun and Dai, Ben},
  booktitle={Advances in Neural Information Processing Systems},
  url={https://arxiv.org/abs/2510.15362},
  year={2025}
}