---
license: apache-2.0
library_name: pytorch
pipeline_tag: image-segmentation
tags:
  - semantic-segmentation
  - semi-supervised-learning
  - contrastive-learning
  - dinov2
  - pytorch
  - cityscapes
  - arxiv:2607.03068
datasets:
  - cityscapes
---

# PixCon — Cityscapes (Clean-Positive Contrastive SSSS)

[![arXiv](https://img.shields.io/badge/arXiv-2607.03068-b31b1b.svg)](https://arxiv.org/abs/2607.03068)

Cityscapes checkpoint for **PixCon**, a clean-positive pixel-contrastive framework over a
DINOv2-Base encoder. PixCon adds one contrastive branch on a UniMatch V2 consistency backbone: a
per-class memory bank admitting **only labeled pixels the student already classifies correctly**
(contamination-free positive set, ρ_F = 0, by construction), with **no inference-time parameters**
and **no bank-specific threshold**. See the [Pascal model](https://huggingface.co/psychofict/pixcon-pascal)
and the paper for the method and analysis.

- **Backbone:** DINOv2-Base (ViT-B/14) + DPT-lite decoder, 19 Cityscapes classes.
- **This checkpoint:** Cityscapes **1/8** split (372 labeled images), **single seed**.

## Results (honest framing)

Compute-matched **one-switch** comparison against our DINOv2 UniMatch V2 reproduction (single seed):

| Split | PixCon | UniMatch V2 (our repro) | Published UM2-B |
|---|---|---|---|
| 1/16 | 83.20 | 83.16 | 83.6 |
| **1/8** | **83.88** | 83.96 | 84.3 |

PixCon **ties** the compute-matched baseline (within seed noise) and sits **at or slightly below the
published UniMatch V2-B** figures. Consistent with the paper's thesis: under a foundation-model
teacher contamination is already rare, so clean-positive contrast is a **no-cost, robust default**
rather than an accuracy booster. These cells are single-seed (see the paper's Cityscapes table).

## Usage

```python
import torch
from torchvision import transforms as T
from PIL import Image
from model.segmentor import PixConSegmentor      # from the PixCon code
from core.inference import whole_inference

model = PixConSegmentor(backbone='dinov2_vitb14', nclass=19, pretrained=False).eval()
sd = torch.load('pixcon_cityscapes_1_8.pth', map_location='cpu')
model.load_state_dict(sd, strict=False)          # proj_head is inference-unused
norm = T.Compose([T.ToTensor(), T.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))])
img = norm(Image.open('example.jpg').convert('RGB')).unsqueeze(0)
with torch.no_grad():
    pred = whole_inference(model, img).argmax(1)  # [1, H, W], 19 Cityscapes classes
```

Interactive demo: [psychofict/pixcon-demo](https://huggingface.co/spaces/psychofict/pixcon-demo).

## Citation

```bibtex
@article{tarubinga2026pixcon,
  title   = {PixCon: Clean-Positive Contrastive Learning for Foundation-Model
             Semi-Supervised Segmentation},
  author  = {Tarubinga, Ebenezer},
  journal = {arXiv preprint arXiv:2607.03068},
  year    = {2026}
}
```