MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning
Paper
•
2505.09265
•
Published
•
5
This repository contains pre-trained weights for the MetaUAS anomaly detection model. This repository contains the paper described in MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning
| File | Description | Size |
|---|---|---|
metauas-256.ckpt |
MetaUAS model (256x256 resolution) | ~85MB |
metauas-512.ckpt |
MetaUAS model (512x512 resolution) | ~85MB |
from huggingface_hub import hf_hub_download
# Download model
model_path = hf_hub_download(
repo_id="your-username/MetaUAS-weights",
filename="metauas-256-v2.ckpt"
)
cc-by-nc-nd-4.0
Base model
google/efficientnet-b4