Loading [a11y]/accessibility-menu.js
Data Augmentation via Latent Space Interpolation for Image Classification | IEEE Conference Publication | IEEE Xplore

Data Augmentation via Latent Space Interpolation for Image Classification


Abstract:

Effective training of the deep neural networks requires much data to avoid underdetermined and poor generalization. Data Augmentation alleviates this by using existing da...Show More

Abstract:

Effective training of the deep neural networks requires much data to avoid underdetermined and poor generalization. Data Augmentation alleviates this by using existing data more effectively. However standard data augmentation produces only limited plausible alternative data by for example, flipping, distorting, adding noise to, cropping a patch from the original samples. In this paper, we introduce the adversarial autoencoder (AAE) to impose the feature representations with uniform distribution and apply the linear interpolation on latent space, which is potential to generate a much broader set of augmentations for image classification. As a possible “recognition via generation” framework, it has potentials for several other classification tasks. Our experiments on the ILSVRC 2012, CIFAR-10 datasets show that the latent space interpolation (LSI) improves the generalization and performance of state-of-the-art deep neural networks.
Date of Conference: 20-24 August 2018
Date Added to IEEE Xplore: 29 November 2018
ISBN Information:
Print on Demand(PoD) ISSN: 1051-4651
Conference Location: Beijing, China

References

References is not available for this document.