Mask2former Swin Large Cityscapes Instance

🚀 Mask2Former

The Mask2Former model is trained on Cityscapes instance segmentation (large-sized version, Swin backbone). It offers a unified approach for instance, semantic, and panoptic segmentation.

🚀 Quick Start

The Mask2Former model trained on Cityscapes instance segmentation (large - sized version, Swin backbone) was introduced in the paper Masked - attention Mask Transformer for Universal Image Segmentation and first released in this repository.

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.

✨ Features

• Unified Segmentation Paradigm: Mask2Former addresses instance, semantic, and panoptic segmentation using the same approach, treating all three tasks as instance segmentation by predicting a set of masks and corresponding labels.
• Performance and Efficiency: It outperforms the previous SOTA, MaskFormer, in both performance and efficiency through several key improvements:
  • Advanced Attention Mechanism: Replaces the pixel decoder with a more advanced multi - scale deformable attention Transformer.
  • Masked Attention Decoder: Adopts a Transformer decoder with masked attention to boost performance without additional computation.
  • Efficient Training: Improves training efficiency by calculating the loss on subsampled points instead of whole masks.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

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


# load Mask2Former fine-tuned on Cityscapes instance segmentation
processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-large-cityscapes-instance")
model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-large-cityscapes-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"]

Advanced Usage

No advanced usage code examples are provided in the original document, so this part is skipped.

📚 Documentation

Intended uses & limitations

You can use this particular checkpoint for instance segmentation. See the model hub to look for other fine - tuned versions on a task that interests you.

How to use

For more code examples, refer to the documentation.

🔧 Technical Details

Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding labels. It outperforms MaskFormer through improvements such as replacing the pixel decoder, adopting a masked - attention Transformer decoder, and improving training efficiency by calculating loss on subsampled points.

📄 License

The license for this model is "other".