---
title: mask2former-swin-tiny-coco-instance
canonical_url: "https://www.modelscope.cn/models/facebook/mask2former-swin-tiny-coco-instance"
md_url: "https://www.modelscope.cn/models/facebook/mask2former-swin-tiny-coco-instance.md"
repository: facebook/mask2former-swin-tiny-coco-instance
last_updated: 2025-05-20
license: other
pipeline_tag: image-segmentation
tasks:
  - image-segmentation
model_type:
  - mask2former
architectures:
  - Mask2FormerForUniversalSegmentation
parameters: 47.5M
tensor_type:
  - F32
  - I64
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
downloads: 501
stars: 0
tags:
  - vision
  - image-segmentation
---

# mask2former-swin-tiny-coco-instance

> mask2former-swin-tiny-coco-instance - facebook 在 ModelScope 开源的模型。Mask2Former model trained on COCO instance segmentation (tiny-sized version, Swin backbone). It was introduced in the paper Masked-attention Mask Transformer for Universal Image Segmentation…

facebook/mask2former-swin-tiny-coco-instance 是 ModelScope 魔搭社区上的 47.5M 参数image-segmentation模型，采用 other 许可。

- **Repository**: facebook/mask2former-swin-tiny-coco-instance
- **License**: other
- **Tasks**: image-segmentation
- **Parameters**: 47.5M
- **Tags**: vision, image-segmentation
- **Downloads**: 501
- **Stars**: 0
- **Last updated**: 2025-05-20

Source: https://www.modelscope.cn/models/facebook/mask2former-swin-tiny-coco-instance

---

# Mask2Former

Mask2Former model trained on COCO instance segmentation (tiny-sized version, Swin backbone). It was introduced in the paper [Masked-attention Mask Transformer for Universal Image Segmentation
](https://arxiv.org/abs/2112.01527) and first released in [this repository](https://github.com/facebookresearch/Mask2Former/). 

Disclaimer: The team releasing Mask2Former did not write a model card for this model so this model card has been written by the Hugging Face team.

## Model description

Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. Hence, all 3 tasks are treated as if they were instance segmentation. Mask2Former outperforms the previous SOTA, 
[MaskFormer](https://arxiv.org/abs/2107.06278) both in terms of performance an efficiency by (i) replacing the pixel decoder with a more advanced multi-scale deformable attention Transformer, (ii) adopting a Transformer decoder with masked attention to boost performance without
without introducing additional computation and (iii) improving training efficiency by calculating the loss on subsampled points instead of whole masks.

![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/mask2former_architecture.png)

## Intended uses & limitations

You can use this particular checkpoint for instance segmentation. See the [model hub](https://huggingface.co/models?search=mask2former) to look for other
fine-tuned versions on a task that interests you.

### How to use

Here is how to use this model:

```python
import requests
import torch
from PIL import Image
from transformers import AutoImageProcessor, Mask2FormerForUniversalSegmentation


# load Mask2Former fine-tuned on COCO instance segmentation
processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-tiny-coco-instance")
model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-tiny-coco-instance")

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(images=image, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)

# model predicts class_queries_logits of shape `(batch_size, num_queries)`
# and masks_queries_logits of shape `(batch_size, num_queries, height, width)`
class_queries_logits = outputs.class_queries_logits
masks_queries_logits = outputs.masks_queries_logits

# you can pass them to processor for postprocessing
result = processor.post_process_instance_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
# we refer to the demo notebooks for visualization (see "Resources" section in the Mask2Former docs)
predicted_instance_map = result["segmentation"]
```

For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/mask2former).