Structured (De)composable representations trained with neural networks

1Citations
Citations of this article
7Readers
Mendeley users who have this article in their library.

Abstract

This paper proposes a novel technique for representing templates and instances of concept classes. A template representation refers to the generic representation that captures the characteristics of an entire class. The proposed technique uses end-to-end deep learning to learn structured and composable representations from input images and discrete labels. The obtained representations are based on distance estimates between the distributions given by the class label and those given by contextual information, which are modeled as environments. We prove that the representations have a clear structure allowing decomposing the representation into factors that represent classes and environments. We evaluate our novel technique on classification and retrieval tasks involving different modalities (visual and language data). In various experiments, we show how the representations can be compressed and how different hyperparameters impact performance.

Cite

CITATION STYLE

APA

Spinks, G., & Moens, M. F. (2020). Structured (De)composable representations trained with neural networks. Computers, 9(4), 1–23. https://doi.org/10.3390/computers9040079

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free