Learning from Synthetic Data Using a Stacked Multichannel Autoencoder

Abstract

Learning from synthetic data has many important and practical applications. An example of application is photo-sketch recognition. Using synthetic data is challenging due to the differences in feature distributions between synthetic and real data, a phenomenon we term synthetic gap. In this paper, we investigate and formalize a general framework-Stacked Multichannel Autoencoder (SMCAE) that enables bridging the synthetic gap and learning from synthetic data more efficiently. In particular, we show that our SMCAE can not only transform and use synthetic data on the challenging face-sketch recognition task, but that it can also help simulate real images, which can be used for training classifiers for recognition. Preliminary experiments validate the effectiveness of the framework.

References in corpus (1)

• Deeply Coupled Auto-encoder Networks for Cross-view Classification

Cited by in corpus (4)

• Algorithms for Semantic Segmentation of Multispectral Remote Sensing Imagery using Deep Learning
• Supervised COSMOS Autoencoder: Learning Beyond the Euclidean Loss!
• Generating Image Sequence from Description with LSTM Conditional GAN
• Segment-Based Credit Scoring Using Latent Clusters in the Variational Autoencoder