Common Representation Learning Using Step-based Correlation Multi-Modal CNN
This work addresses the challenge of multi-modal data integration for researchers in machine learning, but it appears incremental as it builds on existing autoencoder-based approaches.
The paper tackles the problem of learning a common representation for multi-view data by proposing a step-based correlation multi-modal CNN (CorrMCNN) that reconstructs one view from another while enhancing interaction at each hidden layer, achieving better performance than state-of-the-art techniques on benchmark datasets like MNIST and XRMB.
Deep learning techniques have been successfully used in learning a common representation for multi-view data, wherein the different modalities are projected onto a common subspace. In a broader perspective, the techniques used to investigate common representation learning falls under the categories of canonical correlation-based approaches and autoencoder based approaches. In this paper, we investigate the performance of deep autoencoder based methods on multi-view data. We propose a novel step-based correlation multi-modal CNN (CorrMCNN) which reconstructs one view of the data given the other while increasing the interaction between the representations at each hidden layer or every intermediate step. Finally, we evaluate the performance of the proposed model on two benchmark datasets - MNIST and XRMB. Through extensive experiments, we find that the proposed model achieves better performance than the current state-of-the-art techniques on joint common representation learning and transfer learning tasks.