Hadamard Product for Low-rank Bilinear Pooling
Jin-Hwa Kim, Kyoung-Woon On, Woosang Lim, Jeonghee Kim, Jung-Woo Ha, Byoung-Tak Zhang
Abstract
Bilinear models provide rich representations compared with linear models. They have been applied in various visual tasks, such as object recognition, segmentation, and visual question-answering, to get state-of-the-art performances taking advantage of the expanded representations. However, bilinear representations tend to be high-dimensional, limiting the applicability to computationally complex tasks. We propose low-rank bilinear pooling using Hadamard product for an efficient attention mechanism of multimodal learning. We show that our model outperforms compact bilinear pooling in visual question-answering tasks with the state-of-the-art results on the VQA dataset, having a better parsimonious property.
BibTeX
@inproceedings{
kim2017hadamard,
title={Hadamard Product for Low-rank Bilinear Pooling},
author={Jin-Hwa Kim and Kyoung-Woon On and Woosang Lim and Jeonghee Kim and Jung-Woo Ha and Byoung-Tak Zhang},
booktitle={International Conference on Learning Representations},
year={2017},
url={https://openreview.net/forum?id=r1rhWnZkg}
}