Mask2former Swin Large Ade Semantic

🚀 Mask2Former

The Mask2Former model is trained on ADE20k semantic segmentation (large - sized version, Swin backbone). It offers a unified approach to address multiple image segmentation tasks.

🚀 Quick Start

The Mask2Former model is designed to handle instance, semantic, and panoptic segmentation within the same framework. It was introduced in the paper Masked - attention Mask Transformer for Universal Image Segmentation and initially released in this repository.

✨ Features

• Unified Segmentation Paradigm: Addresses instance, semantic, and panoptic segmentation by predicting a set of masks and corresponding labels, treating all three tasks as instance segmentation.
• Performance and Efficiency: Outperforms the previous SOTA, MaskFormer, through several improvements:
  • Replaces the pixel decoder with a more advanced multi - scale deformable attention Transformer.
  • Adopts a Transformer decoder with masked attention to enhance performance without extra computation.
  • 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.

💻 Usage Examples

Basic Usage

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

# load Mask2Former fine - tuned on ADE20k semantic segmentation
processor = AutoImageProcessor.from_pretrained("facebook/mask2former-swin-large-ade-semantic")
model = Mask2FormerForUniversalSegmentation.from_pretrained("facebook/mask2former-swin-large-ade-semantic")

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
predicted_semantic_map = processor.post_process_semantic_segmentation(outputs, target_sizes=[image.size[::-1]])[0]
# we refer to the demo notebooks for visualization (see "Resources" section in the Mask2Former docs)

Advanced Usage

For more code examples, refer to the documentation.

📚 Documentation

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 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 introducing additional computation and (iii) improving training efficiency by calculating the loss on subsampled points instead of whole masks.

Intended uses & limitations

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

🔧 Technical Details

No specific technical details beyond the model description are provided in the original document.

📄 License

The license for this model is "other".