Hadamard Product for Low-rank Bilinear Pooling
Jin-Hwa Kim, Kyoung-Woon On, Woosang Lim, Jeonghee Kim, Jung-Woo Ha, Byoung-Tak Zhang
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/jnhwkim/MulLowBiVQAOfficialIn papertorch★ 0
- github.com/vuhoangminh/vqa_medicalpytorch★ 8
- github.com/Cadene/vqa.pytorchpytorch★ 0
- github.com/MindSpore-scientific/code-8/tree/main/PR_Productmindspore★ 0
- github.com/MindSpore-scientific-2/code-8/tree/main/PR_Productmindspore★ 0
- github.com/MindSpore-scientific-2/code-10/tree/main/PR_Productmindspore★ 0
- github.com/jnhwkim/nips-mrn-vqatorch★ 0
- github.com/Adam1679/mutan-article-netpytorch★ 0
- github.com/yikang-li/iqanpytorch★ 0
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.