4 papers
Training-Free Zero-Shot Anomaly Detection in 3D Brain MRI with 2D Foundation Models
Tai Le-Gia, Jaehyun Ahn
Zero-shot anomaly detection (ZSAD) has gained increasing attention in medical imaging as a way to identify abnormalities without task-specific supervision, but most advances remain…
On the Problem of Consistent Anomalies in Zero-Shot Industrial Anomaly Detection
Tai Le-Gia, Ahn Jaehyun
Zero-shot image anomaly classification (AC) and segmentation (AS) are vital for industrial quality control, detecting defects without prior training data. Existing representation-b…
Breaking MLPerf Training: A Case Study on Optimizing BERT
Yongdeok Kim, Jaehyung Ahn, Myeongwoo Kim +11
Speeding up the large-scale distributed training is challenging in that it requires improving various components of training including load balancing, communication, optimizers, et…
Understanding normalization in contrastive representation learning and out-of-distribution detection
Tai Le-Gia, Jaehyun Ahn
Contrastive representation learning has emerged as an outstanding approach for anomaly detection. In this work, we explore the -norm of contrastive features and its applica…