Zero-Shot Anomaly Detection with Pre-trained Segmentation Models
This work addresses anomaly detection in computer vision for applications like quality control, but it is incremental as it builds on the WINCLIP framework.
The paper tackled zero-shot anomaly detection by integrating segmentation models to improve localization and focusing on relevant image parts, achieving third place in the VAND challenge with an average F1-max score of 81.5/24.2 on the VisA dataset.
This technical report outlines our submission to the zero-shot track of the Visual Anomaly and Novelty Detection (VAND) 2023 Challenge. Building on the performance of the WINCLIP framework, we aim to enhance the system's localization capabilities by integrating zero-shot segmentation models. In addition, we perform foreground instance segmentation which enables the model to focus on the relevant parts of the image, thus allowing the models to better identify small or subtle deviations. Our pipeline requires no external data or information, allowing for it to be directly applied to new datasets. Our team (Variance Vigilance Vanguard) ranked third in the zero-shot track of the VAND challenge, and achieve an average F1-max score of 81.5/24.2 at a sample/pixel level on the VisA dataset.