This is the extended VisA dataset with the ground truth segmentations for each defect types for each image. It represents the dataset along with the paper "MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning" which is published on ICCV 2025 conference.
VisA_Extended/
|-- candle/
|-----|--- Data/
|-----|-----|---- Anomaly_grouped/
|-----|-----|------------|----- 000/… See the full description on the dataset page:
https://huggingface.co/datasets/zhKingg/VisA_Extended.
