MaskLayer: Enabling scalable deep learning solutions by training embedded feature sets

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Deep learning-based methods have shown to achieve excellent results in a variety of domains, however, some important assets are absent. Quality scalability is one of them. In this work, we introduce a novel and generic neural network layer, named MaskLayer. It can be integrated in any feedforward network, allowing quality scalability by design by creating embedded feature sets. These are obtained by imposing a specific structure of the feature vector during training. To further improve the performance, a masked optimizer and a balancing gradient rescaling approach are proposed. Our experiments show that the cost of introducing scalability using MaskLayer remains limited. In order to prove its generality and applicability, we integrated the proposed techniques in existing, non-scalable networks for point cloud compression and semantic hashing with excellent results. To the best of our knowledge, this is the first work presenting a generic solution able to achieve quality scalable results within the deep learning framework.
Original languageEnglish
Pages (from-to)43-53
Number of pages11
JournalNeural Networks
Volume137
DOIs
Publication statusPublished - May 2021

Fingerprint

Dive into the research topics of 'MaskLayer: Enabling scalable deep learning solutions by training embedded feature sets'. Together they form a unique fingerprint.

Cite this