---
license: apache-2.0
library_name: transformers
pipeline_tag: image-feature-extraction
tags:
  - vision
  - feature-extraction
---

# SigLino-30M

**Accepted at CVPR 2026**

[![Project Website](https://img.shields.io/badge/Project-Website-blue)](https://sofianchay.github.io/siglino/)
[![arXiv](https://img.shields.io/badge/arXiv-2512.20157-b31b1b.svg)](https://arxiv.org/abs/2512.20157)
[![GitHub](https://img.shields.io/badge/GitHub-Code-black)](https://github.com/tiiuae/siglino)

This work stems from the **CVPR 2026 AMoE paper**, which designs and applies distillation into a Mixture-of-Experts (MoE) vision architecture. We have chosen the name **SigLino** for better clarity (SigLIP2 + DINOv3).

Dense variant of SigLino. 30M parameters.

Part of the [SigLino model family](https://huggingface.co/collections/tiiuae/siglino-vision-foundation-models).

## Usage

```python
import torch
from PIL import Image
from transformers import AutoModel, AutoImageProcessor

model_id = "tiiuae/siglino-30M"
model = AutoModel.from_pretrained(model_id, trust_remote_code=True).to("cuda", dtype=torch.bfloat16)
processor = AutoImageProcessor.from_pretrained(model_id, trust_remote_code=True)

image = Image.open("image.jpg").convert("RGB")
inputs = processor(image, return_tensors="pt").to("cuda")
inputs["pixel_values"] = inputs["pixel_values"].to(torch.bfloat16)

with torch.no_grad():
    outputs = model(**inputs)

# Options: 'siglino' (384d), 'siglip2' (1152d), 'dinov3' (1024d)
patch_features = outputs["patch_features"]["siglino"]         # (Batch, Tokens, 384)
summary_features = outputs["summary_features"]["siglip2"]  # (Batch, 1152)
```

## Model Details

| Property | Value |
|----------|-------|
| Architecture | Dense |
| Parameters | 0.03B |
| Layers | 12 |
| Hidden Dim | 384 |
| FFN Dim | 1536 |
| Patch Size | 16x16 |
| Teachers | DINOv3, SigLIP2 |

## Results (512x512, ensemble features)

| Task | Metric | Score |
|------|--------|-------|
| kNN (ImageNet) | Acc | 79.0 |
| kNN (6-dataset avg) | Acc | 83.3 |
| Zero-shot cls (ImageNet) | Acc | 65.1 |
| Flickr30K I2T | R@1 | 82.2 |
| MSCOCO I2T | R@1 | 59.7 |
| Pascal VOC (1024) | mIoU | 82.1 |
| Cityscapes (1024) | mIoU | 59.2 |

## Citation

```bibtex
@article{chaybouti2025amoe,
  title={AMoE: Agglomerative Mixture-of-Experts Vision Foundation Models},
  author={Chaybouti, Sofian and Narayan, Sanath and Dahou, Yasser and Le Khac, Phuc H. and Singh, Ankit and Huynh, Ngoc Dung and Para, Wamiq Reyaz and Kuehne, Hilde and Hacid, Hakim},
  journal={arXiv preprint arXiv:2512.20157},
  year={2025}
}
```