3 papers
cs.CV2026
Domain Adaptation of Attention Heads for Zero-shot Anomaly Detection
Kiyoon Jeong, Jaehyuk Heo, Junyeong Son +1
Zero-shot anomaly detection (ZSAD) enables anomaly detection without normal samples from target categories, addressing scenarios where task-specific training data is unavailable. H…
cs.CV2025
Multi-class Image Anomaly Detection for Practical Applications: Requirements and Robust Solutions
Jaehyuk Heo, Pilsung Kang
Recent advances in image anomaly detection have extended unsupervised learning-based models from single-class settings to multi-class frameworks, aiming to improve efficiency in tr…
cs.CV2025
Avoid Wasted Annotation Costs in Open-set Active Learning with Pre-trained Vision-Language Model
Jaehyuk Heo, Pilsung Kang
Active learning (AL) aims to enhance model performance by selectively collecting highly informative data, thereby minimizing annotation costs. However, in practical scenarios, unla…