EE-AE: An Exclusivity Enhanced Unsupervised Feature Learning Approach
This work addresses overfitting in unsupervised feature learning for data representation, but it appears incremental as it builds on conventional autoencoders.
The paper tackles the problem of overfitting in autoencoders by proposing an Exclusivity Enhanced (EE) approach that incorporates statistical and geometrical dependencies, achieving remarkable performance compared to related methods.
Unsupervised learning is becoming more and more important recently. As one of its key components, the autoencoder (AE) aims to learn a latent feature representation of data which is more robust and discriminative. However, most AE based methods only focus on the reconstruction within the encoder-decoder phase, which ignores the inherent relation of data, i.e., statistical and geometrical dependence, and easily causes overfitting. In order to deal with this issue, we propose an Exclusivity Enhanced (EE) unsupervised feature learning approach to improve the conventional AE. To the best of our knowledge, our research is the first to utilize such exclusivity concept to cooperate with feature extraction within AE. Moreover, in this paper we also make some improvements to the stacked AE structure especially for the connection of different layers from decoders, this could be regarded as a weight initialization trial. The experimental results show that our proposed approach can achieve remarkable performance compared with other related methods.