---
license: mit
library_name: BEVANet
tags:
- image-segmentation
- real-time-semantic-segmentation
- real-time
- semantic-segmentation
- computer-vision
- pytorch
datasets:
- Cityscapes
metrics:
- mIoU
- FPS
---


<div align="center">
<h1> BEVANet: Bilateral Efficient Visual Attention Network for Real-Time Semantic Segmentation (ICIP 2025 spotlight) </h1>

[![arXiv paper](https://img.shields.io/badge/arXiv%20paper-2508.07300-red.svg?logo=arXiv)](https://arxiv.org/abs/2508.07300)
[![ICIP paper](https://img.shields.io/badge/IEEE%20paper-ICIP25%20spotlight-blue.svg?logo=IEEE)](https://ieeexplore.ieee.org/document/11084676)
[![GitHub Code](https://img.shields.io/badge/Code-GitHub-black.svg?logo=github)](https://github.com/maomao0819/BEVANet)
[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)

[Ping-Mao Huang](https://www.linkedin.com/in/maomao0819/), I-Tien Chao, Ping-Chia Huang, Jia-Wei Liao, Yung-Yu Chuang<br>
National Taiwan University

</div>

## Model Description

- **Task**: Real-Time Semantic Segmentation
- **Dataset**: Cityscapes
- **Model**: BEVANet

BEVANet semantic segmentation model trained on Cityscapes dataset. Achieves 81.0% mIoU with 32.8 FPS on RTX3090.

## Performance

- **mIoU**: 81.0%
- **FPS**: 32.8 (RTX3090)
- **Parameters**: 58.6M

## Usage

```python
from models.BEVANet import BEVANet_SEG

# Load model from specific branch
model = BEVANet_SEG.from_pretrained(
    "maomao0819/BEVANet", 
    revision="main"
)

# For main branch (no revision needed)
# model = BEVANet_SEG.from_pretrained("maomao0819/BEVANet")
```

## All Model Variants

| Model | Branch | Dataset | Task | Performance | FPS | Parameters |
|-------|--------|---------|------|-------------|-----|------------|
| BEVANet-S | `imagenet-bevanet-s` | ImageNet | Classification | 71.1% Top-1 | 198.6 | 16.3M |
| BEVANet | `imagenet-bevanet` | ImageNet | Classification | 76.3% Top-1 | 82.3 | 57.4M |
| BEVANet-S | `cityscapes-bevanet-s` | Cityscapes | Segmentation | 78.2% mIoU | 70.0 | 15.2M |
| BEVANet | `main` | Cityscapes | Segmentation | 81.0% mIoU | 32.8 | 58.6M |
| BEVANet-S | `camvid-bevanet-s` | CamVid | Segmentation | 83.1% mIoU | 79.4 | 15.2M |
| BEVANet | `ade20k-bevanet` | ADE20K | Segmentation | 39.8% mIoU | 73.3 | 58.9M |

## Citation

If you use this model, please cite:

```bibtex
@inproceedings{huang2025bevanet,
  title={Bevanet: Bilateral Efficient Visual Attention Network for Real-Time Semantic Segmentation},
  author={Huang, Ping-Mao and Chao, I-Tien and Huang, Ping-Chia and Liao, Jia-Wei and Chuang, Yung-Yu},
  booktitle={2025 IEEE International Conference on Image Processing (ICIP)},
  pages={2778--2783},
  year={2025},
  organization={IEEE}
}
```