---
license: apache-2.0
library_name: libreyolo
pipeline_tag: image-segmentation
tags:
  - image-segmentation
  - semantic-segmentation
  - lingbot-vision
  - vision-transformer
  - ade20k
datasets:
  - ade20k
---

# LibreLingBotVisionb-sem

LingBot-Vision ViT-B/16 (86M backbone) self-supervised backbone with a LibreYOLO-trained 1x1
dense head for ADE20K 150-class semantic segmentation at 512x512.

## Source

The backbone derives from [robbyant/lingbot-vision](https://github.com/robbyant/lingbot-vision)
("Vision Pretraining for Dense Spatial Perception", Fu et al., 2026,
arXiv:2607.05247), weights from
[robbyant/lingbot-vision-vit-base](https://huggingface.co/robbyant/lingbot-vision-vit-base).
Copyright (c) 2026 Robbyant. Licensed under the Apache License 2.0.

## Modifications

The backbone tensors are unchanged (the LibreYOLO port is parity-verified at
max_abs_diff == 0 against the reference implementation). The dense head is a
1x1 convolution over the frozen patch-token grid, trained by LibreYOLO on
ADE20K following the linear-probing protocol of the upstream technical
report (ADE20K val mIoU 50.1 at 512x512, single scale; upstream linear-probe reference 51.4). Conversion and metadata wrapping:
`weights/convert_lingbotvision_weights.py` in the
[LibreYOLO source repository](https://github.com/LibreYOLO/libreyolo).

## Usage

```python
from libreyolo import LibreYOLO

model = LibreYOLO("LibreLingBotVisionb-sem.pt")
results = model.predict("image.jpg")
results.save("out.jpg")
```

Fine-tune on your own semantic dataset (head-only by default, matching the
linear-probe recipe; pass `freeze_backbone=False` for a full fine-tune):

```python
model.train(data="your_semantic.yaml", epochs=20)
```

## License

Apache License 2.0. See the [`LICENSE`](./LICENSE) and [`NOTICE`](./NOTICE)
files in this repository.

## Dataset Note

ADE20K has separate dataset terms and is not redistributed in this repository.