Hierarchical Question-Image Co-Attention for Visual Question Answering

TL;DR

This paper introduces a hierarchical co-attention model for VQA that jointly models image and question attention, leading to improved accuracy on standard datasets.

Contribution

It proposes a novel joint co-attention mechanism with hierarchical reasoning using CNNs, advancing the state-of-the-art in visual question answering.

Findings

Achieved new state-of-the-art accuracy on VQA and COCO-QA datasets.

Demonstrated the effectiveness of hierarchical question-image attention.

Improved performance with ResNet features.

Abstract

A number of recent works have proposed attention models for Visual Question Answering (VQA) that generate spatial maps highlighting image regions relevant to answering the question. In this paper, we argue that in addition to modeling "where to look" or visual attention, it is equally important to model "what words to listen to" or question attention. We present a novel co-attention model for VQA that jointly reasons about image and question attention. In addition, our model reasons about the question (and consequently the image via the co-attention mechanism) in a hierarchical fashion via a novel 1-dimensional convolution neural networks (CNN). Our model improves the state-of-the-art on the VQA dataset from 60.3% to 60.5%, and from 61.6% to 63.3% on the COCO-QA dataset. By using ResNet, the performance is further improved to 62.1% for VQA and 65.4% for COCO-QA.