Search Results - "Yoa, Seungdong"

Self-Supervised Learning for Anomaly Detection With Dynamic Local Augmentation by Yoa, Seungdong, Lee, Seungjun, Kim, Chiyoon, Kim, Hyunwoo J

“…Anomaly detection is an important problem for recent advances in machine learning. To this end, many attempts have emerged to detect unknown anomalies of the…”
Get full text

Learning Non-Parametric Surrogate Losses With Correlated Gradients by Yoa, Seungdong, Park, Jinyoung, Kim, Hyunwoo J.

“…Training models by minimizing surrogate loss functions with gradient-based algorithms is a standard approach in various vision tasks. This strategy often leads…”
Get full text

Learning to Balance Local Losses via Meta-Learning by Yoa, Seungdong, Jeon, Minkyu, Oh, Youngjin, Kim, Hyunwoo J.

“…The standard training for deep neural networks relies on a global and fixed loss function. For more effective training, dynamic loss functions have been…”
Get full text

Learning to Balance Local Losses via Meta-Learning by Yoa, Seungdong, Jeon, Minkyu, Oh, Youngjin, Kim, Hyunwoo J

“…The standard training for deep neural networks relies on a global and fixed loss function. For more effective training, dynamic loss functions have been…”
Get full text