Multimodal Integration of Human-Like Attention in Visual Question Answering

Abstract

Human-like attention as a supervisory signal to guide neural attention has shown significant promise but is currently limited to uni-modal integration - even for inherently multimodal tasks such as visual question answering (VQA). We present the Multimodal Human-like Attention Network (MULAN) - the first method for multimodal integration of human-like attention on image and text during training of VQA models. MULAN integrates attention predictions from two state-of-the-art text and image saliency models into neural self-attention layers of a recent transformer-based VQA model. Through evaluations on the challenging VQAv2 dataset, we show that MULAN achieves a new state-of-the-art performance of 73.98% accuracy on test-std and 73.72% on test-dev and, at the same time, has approximately 80% fewer trainable parameters than prior work. Overall, our work underlines the potential of integrating multimodal human-like and neural attention for VQA

References in corpus (5)

• Seeing with Humans: Gaze-Assisted Neural Image Captioning
• Exploring Human-like Attention Supervision in Visual Question Answering
• Improving Natural Language Processing Tasks with Human Gaze-Guided Neural Attention
• VQA-MHUG: A Gaze Dataset to Study Multimodal Neural Attention in Visual Question Answering
• AiR: Attention with Reasoning Capability

Cited by in corpus (2)

• Integrating Cognitive Processing Signals into Language Models: A Review of Advances, Applications and Future Directions
• Causal Debiasing for Visual Commonsense Reasoning