no code implementations • 28 Mar 2024 • Hyejin Park, Jeongyeon Hwang, Sunung Mun, Sangdon Park, Jungseul Ok
In response to the emerging threat, we propose median batch normalization (MedBN), leveraging the robustness of the median for statistics estimation within the batch normalization layer during test-time inference.
no code implementations • 11 Sep 2023 • Jaechang Kim, Jeongyeon Hwang, Soheun Yi, Jaewoong Cho, Jungseul Ok
Neural networks often suffer from a feature preference problem, where they tend to overly rely on specific features to solve a task while disregarding other features, even if those neglected features are essential for the task.