Mind the prompt: A novel benchmark for prompt-based class-agnostic counting
Class-agnostic counting (CAC) is a recent task in computer vision that aims to estimate the
number of instances of arbitrary object classes never seen during model training. With the …
number of instances of arbitrary object classes never seen during model training. With the …
SOWA: Adapting Hierarchical Frozen Window Self-Attention to Visual-Language Models for Better Anomaly Detection
Z Hu, Z Zhang - arxiv preprint arxiv:2407.03634, 2024 - arxiv.org
Visual anomaly detection is critical in industrial manufacturing, but traditional methods often
rely on extensive normal datasets and custom models, limiting scalability. Recent …
rely on extensive normal datasets and custom models, limiting scalability. Recent …
FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model
Y Li, E Ivanova, M Bruveris - arxiv preprint arxiv:2409.00556, 2024 - arxiv.org
Automatic image anomaly detection is important for quality inspection in the manufacturing
industry. The usual unsupervised anomaly detection approach is to train a model for each …
industry. The usual unsupervised anomaly detection approach is to train a model for each …