MAEDAY: MAE for few- and zero-shot AnomalY-Detection
Authors:
- Eli SchwartzESEli Schwartz
- Assaf ArbelleAAAssaf Arbelle
- Leonid KarlinskyLKLeonid Karlinsky
- Sivan HararySHSivan Harary
- Florian ScheideggerFSFlorian Scheidegger
- Sivan DovehSDSivan Doveh
- Raja GiryesRGRaja Giryes
- 16 February 2024
- journal article
- research article
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 241
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- European Research Council
This publication has 16 references indexed in Scilit:
- WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation2023
- Towards optimal foreign object debris detection in an airport environmentExpert Systems with Applications, 2022
- Towards Total Recall in Industrial Anomaly Detection2022
- Masked Autoencoders Are Scalable Vision Learners2022
- AnoDDPM: Anomaly Detection with Denoising Diffusion Probabilistic Models using Simplex Noise2022
- MetAdapt: Meta-learned task-adaptive architecture for few-shot classificationPattern Recognition Letters, 2021
- CutPaste: Self-Supervised Learning for Anomaly Detection and Localization2021
- Reconstruction by inpainting for visual anomaly detectionPattern Recognition, 2021
- The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly DetectionInternational Journal of Computer Vision, 2021
- Anomaly detection through registrationPattern Recognition, 1999