arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.09192cs.LGcs.CLcs.CVstat.ML
收藏

基于稀疏混合专家混合专家模型的可视化问答

Learning Sparse Mixture of Experts for Visual Question Answering

Mila(米拉);Université de Montréal(蒙特利尔大学);Polytechnique Montréal(蒙特利尔高等理工学院)

Vardaan Pahuja, Jie Fu, Christopher J. Pal

摘要:

随着模型结构的改进,可视化问答的任务取得了快速的进展。不幸的是,这些模型通常是计算密集型的,由于其庞大的规模,这对部署构成了严重的挑战。我们的目标是解决这个问题的视觉问答(VQA)的具体任务。卷积神经网络(CNN)是VQA模型的视觉处理管道的组成部分(假设CNN与整个VQA模型一起训练)。在这个项目中,我们提出了一个有效的和模块化的神经架构的VQA任务的重点是CNN模块。我们的实验表明,一个稀疏激活的CNN为基础的VQA模型实现了相当的性能标准的CNN为基础的VQA模型架构。

英文摘要:

There has been a rapid progress in the task of Visual Question Answering with improved model architectures. Unfortunately, these models are usually computationally intensive due to their sheer size which poses a serious challenge for deployment. We aim to tackle this issue for the specific task of Visual Question Answering (VQA). A Convolutional Neural Network (CNN) is an integral part of the visual processing pipeline of a VQA model (assuming the CNN is trained along with entire VQA model). In this project, we propose an efficient and modular neural architecture for the VQA task with focus on the CNN module. Our experiments demonstrate that a sparsely activated CNN based VQA model achieves comparable performance to a standard CNN based VQA model architecture.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑