신경망 모델의 편향성을 줄이기 위한 데이터 증강 연구

A Study of Mixed Augmentation for Reducing Model Bias

Recent studies demonstrate that deep learning model is easily biased by trained with unbalanced datasets. For example, the deep network can be trained to make a prediction by background feature instead the real target's feature. For those problem, a measurement called leakage was introduced to digitize this tendency. In this paper, we propose augmentation strategy which are used generally in computer vision problem to remedy this bias problem and we showed a simple augmentation methods have a effect to this task with experiments.