Re-implementing and Extending Relation Network for R-CBIR

  • Messina N
  • Amato G
  • Falchi F
N/ACitations
Citations of this article
1Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Relational reasoning is an emerging theme in Machine Learning in general and in Computer Vision in particular. Deep Mind has recently proposed a module called Relation Network (RN) that has shown impressive results on visual question answering tasks. Unfortunately, the implementation of the proposed approach was not public. To reproduce their experiments and extend their approach in the context of Information Retrieval, we had to re-implement everything, testing many parameters and conducting many experiments. Our implementation is now public on GitHub and it is already used by a large community of researchers. Furthermore, we recently presented a variant of the relation network module that we called Aggregated Visual Features RN (AVF-RN). This network can produce and aggregate at inference time compact visual relationship-aware features for the Relational-CBIR (R-CBIR) task. R-CBIR consists in retrieving images with given relationships among objects. In this paper, we discuss the details of our Relation Network implementation and more experimental results than the original paper. Relational reasoning is a very promising topic for better understanding and retrieving inter-object relationships, especially in digital libraries.

Cite

CITATION STYLE

APA

Messina, N., Amato, G., & Falchi, F. (2020). Re-implementing and Extending Relation Network for R-CBIR (pp. 82–92). https://doi.org/10.1007/978-3-030-39905-4_9

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