Modulated Self-attention Convolutional Network for VQA
arXiv:1910.03343
Abstract
As new data-sets for real-world visual reasoning and compositional question answering are emerging, it might be needed to use the visual feature extraction as a end-to-end process during training. This small contribution aims to suggest new ideas to improve the visual processing of traditional convolutional network for visual question answering (VQA). In this paper, we propose to modulate by a linguistic input a CNN augmented with self-attention. We show encouraging relative improvements for future research in this direction.
Accepted at NeurIPS 2019 workshop: ViGIL
References in corpus (6)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Self-Attention Generative Adversarial Networks
- Wide Residual Networks
- Hierarchical Question-Image Co-Attention for Visual Question Answering
- VQA: Visual Question Answering
- Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering