---
license: mit
tags:
  - kornia
  - feature-description
  - patch-descriptor
---

# kornia/hynet

Pretrained weights for **HyNet**,
used by [`kornia.feature.HyNet`](https://kornia.readthedocs.io/en/latest/feature.html).

HyNet is a 128-dimensional patch descriptor that replaces batch normalisation with
Filter Response Normalisation and trains with a hybrid similarity measure combining
L2 distance and cosine similarity under a triplet margin loss. NeurIPS 2020.

**Original repo:** [yuruntian/HyNet](https://github.com/yuruntian/HyNet)

## Weights

| File | Training data |
|------|--------------|
| `HyNet_LIB.pth` | Liberty |
| `HyNet_ND.pth` | Notre Dame |
| `HyNet_YOS.pth` | Yosemite |

## Citation

```bibtex
@inproceedings{hynet2020,
    author    = {Tian, Yurun and Barroso Laguna, Axel and Ng, Tony
                 and Balntas, Vassileios and Mikolajczyk, Krystian},
    title     = {{HyNet}: Learning Local Descriptor with Hybrid Similarity
                 Measure and Triplet Loss},
    booktitle = {NeurIPS},
    year      = {2020}
}
```