Deep Exemplar Networks for VQA and VQG

TL;DR

This paper introduces exemplar-based modules into deep learning architectures for VQA and VQG, demonstrating improved performance and generalization by mimicking human exemplar reliance.

Contribution

It proposes a novel exemplar-based approach that can be integrated into existing deep learning models for VQA and VQG, enhancing their effectiveness.

Findings

Exemplar modules improve VQA and VQG accuracy.

The approach generalizes across multiple architectures.

Empirical results outperform baseline models.

Abstract

In this paper, we consider the problem of solving semantic tasks such as `Visual Question Answering' (VQA), where one aims to answers related to an image and `Visual Question Generation' (VQG), where one aims to generate a natural question pertaining to an image. Solutions for VQA and VQG tasks have been proposed using variants of encoder-decoder deep learning based frameworks that have shown impressive performance. Humans however often show generalization by relying on exemplar based approaches. For instance, the work by Tversky and Kahneman suggests that humans use exemplars when making categorizations and decisions. In this work, we propose the incorporation of exemplar based approaches towards solving these problems. Specifically, we incorporate exemplar based approaches and show that an exemplar based module can be incorporated in almost any of the deep learning architectures proposed in the literature and the addition of such a block results in improved performance for solving these tasks. Thus, just as the incorporation of attention is now considered de facto useful for solving these tasks, similarly, incorporating exemplars also can be considered to improve any proposed architecture for solving this task. We provide extensive empirical analysis for the same through various architectures, ablations, and state of the art comparisons.