Reasoning Visual Dialogs with Structural and Partial Observations

TL;DR

This paper introduces a novel graph-based model for Visual Dialog that infers dialog structures and answers simultaneously, improving reasoning capabilities and outperforming existing methods on standard datasets.

Contribution

It formalizes Visual Dialog as inference in a graphical model with partial observations and proposes a differentiable GNN solution to infer dialog structures and answers.

Findings

Outperforms comparative methods on VisDial datasets

Successfully infers underlying dialog structures

Enhances dialog reasoning accuracy

Abstract

We propose a novel model to address the task of Visual Dialog which exhibits complex dialog structures. To obtain a reasonable answer based on the current question and the dialog history, the underlying semantic dependencies between dialog entities are essential. In this paper, we explicitly formalize this task as inference in a graphical model with partially observed nodes and unknown graph structures (relations in dialog). The given dialog entities are viewed as the observed nodes. The answer to a given question is represented by a node with missing value. We first introduce an Expectation Maximization algorithm to infer both the underlying dialog structures and the missing node values (desired answers). Based on this, we proceed to propose a differentiable graph neural network (GNN) solution that approximates this process. Experiment results on the VisDial and VisDial-Q datasets show that our model outperforms comparative methods. It is also observed that our method can infer the underlying dialog structure for better dialog reasoning.