---
library_name: visbench
tags:
- visbench
- probing
- semantic_segmentation
---

# semantic_segmentation probe for `dinov2_vitb14`

A **trained probe head**, not a backbone. It is the small module VisBench fits
on top of frozen `dinov2_vitb14` features to measure what those features carry.

```python
import visbench
from visbench.hub import load_probe_from_hub

backbone = visbench.get_backbone("dinov2_vitb14")
probe = load_probe_from_hub("turhancan97/visbench-semantic_segmentation-dinov2_vitb14", backbone=backbone)
```

## It only works with this backbone

These weights were fitted on features from `dinov2_vitb14`, taken with
`pooling=mean` and `feature_mode=dense_only`. Loading them against
anything else is refused, because the failure is otherwise silent: a head fitted
on one pooling and fed another has the right shapes and produces a plausible,
wrong number.

| | |
| --- | --- |
| backbone | `dinov2_vitb14` |
| backbone key | `dinov2/dinov2_vitb14/224/7764ea0f912e` |
| task | `semantic_segmentation` (high_level) |
| pooling | `mean` (requested `mean`) |
| feature mode | `dense_only` |
| layers | `None` |

**Reported scores**

| metric | value |
| --- | --- |
| `mean_acc` | 0.8403 |
| `miou` | 0.7533 |
| `miou_per_image` | 0.7161 |
| `pixel_acc` | 0.9316 |

## Reproducing it

Fitted with:

- `batch_size`: `8`
- `epochs`: `10`
- `head`: `linear`
- `hidden_dim`: `512`
- `ignore_index`: `-1`
- `layers`: `None`
- `loss`: `cross_entropy`
- `lr`: `0.0005`
- `miou_reduction`: `dataset_and_per_image`
- `num_classes`: `21`
- `optimizer`: `adamw`
- `protocol`: `visbench_semantic_seg`
- `warmup_epochs`: `1.5`
- `weight_decay`: `0.0001`

Generated by [VisBench](https://github.com/turhancan97/VisBench).