---
tags:
- pemola
- panoptic-segmentation
- occlusion
- icme-2026
datasets:
- weiwb/COCO-OLAC
- weiwb/Cityscapes-OLAC
---
# PEMOLA (ICME 2026)
Official checkpoints for **[Occlusion-Aware Panoptic Segmentation with Joint Position Embedding and Occlusion-Level Attention](https://huggingface.co/papers/2607.18112)** (ICME 2026).
## Related resources
**Research overview:** [Occlusion-Aware Visual Understanding](https://huggingface.co/collections/weiwb/occlusion-aware-visual-understanding-6ac212311f2153fa719c9f95). Explore the papers, datasets, model checkpoints, and how they relate.
| Resource | What it provides |
|:---------|:-----------------|
| [COCO-OLAC dataset](https://huggingface.co/datasets/weiwb/COCO-OLAC) | Image-level occlusion annotations for 30,000 COCO training images and 5,000 validation images, including validation subsets by occlusion level. |
| [Cityscapes-OLAC dataset](https://huggingface.co/datasets/weiwb/Cityscapes-OLAC) | Image-level occlusion annotations for 2,975 Cityscapes training images and 500 validation images, following the same annotation protocol. |
Both dataset repositories provide additional occlusion annotations. Obtain the original images and segmentation annotations separately from the [official COCO website](https://cocodataset.org/#download) and the [official Cityscapes website](https://www.cityscapes-dataset.com/downloads/).
## Download
Download all models from the PEMOLA source repository root:
```bash
python -m pip install huggingface_hub
hf download weiwb/PEMOLA --local-dir checkpoints
```
To download one model, specify its checkpoint filename:
```bash
hf download weiwb/PEMOLA mask2former_pemola_coco_olac.pth --local-dir checkpoints
```
For source code, [installation](https://github.com/wenbo-wei/PEMOLA#installation), and [inference](https://github.com/wenbo-wei/PEMOLA#inference--visualization), see the [PEMOLA GitHub repository](https://github.com/wenbo-wei/PEMOLA).
### Panoptic Segmentation on COCO-OLAC
| Method |
Backbone |
PQ |
PQTh |
PQSt |
APThpan |
mIoUpan |
Weights |
| Mask2Former |
ResNet-50 |
40.7 |
44.5 |
35.0 |
30.0 |
54.2 |
download |
| + PEMOLA |
ResNet-50 |
41.5 |
45.2 |
35.9 |
30.4 |
54.8 |
download |
| Mask DINO |
ResNet-50 |
44.0 |
48.5 |
37.3 |
33.5 |
53.4 |
download |
| + PEMOLA |
ResNet-50 |
44.8 |
49.4 |
37.8 |
34.2 |
55.3 |
download |
### Panoptic Segmentation on Cityscapes-OLAC
| Method |
Backbone |
PQ |
PQTh |
PQSt |
APThpan |
mIoUpan |
Weights |
| Mask2Former |
ResNet-50 |
61.5 |
54.0 |
66.9 |
35.2 |
76.1 |
download |
| + PEMOLA |
ResNet-50 |
62.3 |
55.4 |
67.2 |
38.5 |
77.4 |
download |
### Occlusion Classifier
Top-1 accuracies (%) reported in the paper on the COCO-OLAC test split with background-blackened inputs, for occlusion classification.
| Backbone |
Pretraining |
Input |
Top-1 Acc (%) |
Weights |
| Swin-L | ImageNet-22K | 384 | 75.3 | download |