papers AI Learner
The Github is limit! Click to go to the new site.

Hadamard Product for Low-rank Bilinear Pooling

2017-03-26
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.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1610.04325

PDF

https://arxiv.org/pdf/1610.04325


Similar Posts

Comments