Missing Modalities Imputation via Cascaded Residual Autoencoder

Citations Over TimeTop 10% of 2017 papers

Abstract

Affordable sensors lead to an increasing interest in acquiring and modeling data with multiple modalities. Learning from multiple modalities has shown to significantly improve performance in object recognition. However, in practice it is common that the sensing equipment experiences unforeseeable malfunction or configuration issues, leading to corrupted data with missing modalities. Most existing multi-modal learning algorithms could not handle missing modalities, and would discard either all modalities with missing values or all corrupted data. To leverage the valuable information in the corrupted data, we propose to impute the missing data by leveraging the relatedness among different modalities. Specifically, we propose a novel Cascaded Residual Autoencoder (CRA) to impute missing modalities. By stacking residual autoencoders, CRA grows iteratively to model the residual between the current prediction and original data. Extensive experiments demonstrate the superior performance of CRA on both the data imputation and the object recognition task on imputed data.

Related Papers

• → A reinforcement learning-based approach for imputing missing data(2022)29 cited
• → Guided Multiple Imputation of Missing Data(2007)52 cited
• → Missing Value Imputation Using a Semi-supervised Rank Aggregation Approach(2008)12 cited
• → Missing Values Imputation Based on Iterative Learning(2013)4 cited
• Application of SOLAS to the Multiple Imputation for Missing Data(2003)