Multi-step Reasoning via Recurrent Dual Attention for Visual Dialog

TL;DR

This paper introduces ReDAN, a multi-step reasoning model for visual dialog that iteratively refines question understanding and visual context to improve answer accuracy, achieving state-of-the-art results on VisDial v1.0.

Contribution

ReDAN employs recurrent dual attention for multi-step reasoning, enhancing visual dialog understanding beyond previous models.

Findings

Achieves 64.47% NDCG score on VisDial v1.0

Demonstrates effective localization of visual and textual clues through iterative reasoning

Outperforms existing models in visual dialog tasks

Abstract

This paper presents a new model for visual dialog, Recurrent Dual Attention Network (ReDAN), using multi-step reasoning to answer a series of questions about an image. In each question-answering turn of a dialog, ReDAN infers the answer progressively through multiple reasoning steps. In each step of the reasoning process, the semantic representation of the question is updated based on the image and the previous dialog history, and the recurrently-refined representation is used for further reasoning in the subsequent step. On the VisDial v1.0 dataset, the proposed ReDAN model achieves a new state-of-the-art of 64.47% NDCG score. Visualization on the reasoning process further demonstrates that ReDAN can locate context-relevant visual and textual clues via iterative refinement, which can lead to the correct answer step-by-step.