MEML: A Deep Data Augmentation Method by Mean Extrapolation in Middle Layers
Dongchen Liu, Lun Zhang, Xiansen Jiang, Caixia Su, Yufeng Fan, Yongfeng Cao · IEEE Access · 2021
Data augmentation, generating new data that are similar but not same with the original data by making a series of transformations to the original data, is one of the mainstream methods to alleviate the problem of insufficient data. Instead of augmenting input data, this paper proposes a method for augmenting features in the middle layers of deep models, called MEML (Mean Extrapolation in Middle Layers). It gets the features outputted by any middle layer of deep models and then creates new features by extrapolating some randomly selected features with their corresponding class mean. After that, it replaces these selected features with the new ones, and then let the new composed output continue to propagate forward. Experiments on two classic deep neural network models and three image datasets show that our MEML method can significantly improve the model classification accuracy and outperform the state-of-the-art feature space augmentation methods such as dropout and K Nearest Neighbors extrapolation in most experiments. Interestingly, when coupled with some input space augmentation methods, e.g., rotation and horizontal flip, MEML could further improve the performance of deep models, implying that the input space augmentation methods and MEML could complement each other.