1 code implementation • 6th Workshop on Meta-Learning at NeurIPS 2022 2022 • Huiwon Jang, Hankook Lee, Jinwoo Shin
Unsupervised meta-learning aims to learn generalizable knowledge across a distribution of tasks constructed from unlabeled data.
no code implementations • 26 Oct 2022 • Yeongmin Kim, Huiwon Jang, DongKeon Lee, Ho-Jin Choi
To break through these observations, we propose a simple solution AltUB which introduces alternating training to update the base distribution of normalizing flow for anomaly detection.
Ranked #2 on Anomaly Detection on BTAD (using extra training data)