.png){kind=icon}
返回
Improving visual question answering using dropout and enhanced question encoder
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2019.01.038.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Using dropout in Visual Question Answering (VQA) is a common practice to prevent overfitting. However, the current way to use dropout in multi-path networks may cause two problems: the co-adaptations of neurons and the explosion of output variance. In this paper, we propose coherent dropout and siamese dropout mechanism to solve the two problems, respectively. Specifically, in coherent dropout, the relevant dropout layers in multiple paths are forced to work coherently to maximize the ability of preventing neuron co-adaptations. We show that the coherent dropout is simple in implementation but very effective to overcome overfitting. As for the explosion of output variance, we develop a siamese dropout mechanism to explicitly minimize the difference between the two output vectors produced from the same input data during training phase. Such mechanism can reduce the gap between training and inference phases and make the VQA model more robust. With the help of the two techniques, we further design an enhanced question encoder called Multi-path Stacked Residual RNNs which is deeper and wider and more powerful than current shallow question encoder. Extensive experiments are conducted to verify the effectiveness of coherent dropout, siamese dropout and the enhanced question encoder. And the results show that our methods can bring clear improvements to the state-of-the-art VQA models on VQA-vl and VQA-v2 datasets. (C) 2019 Elsevier Ltd. All rights reserved.
Keyword:
Visual question answering
Coherent dropout
Siamese dropout
Enhanced question encoder
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations视觉基因组: 使用众包密集图像注释连接语言和视觉
OAAI
OAAI分享收藏Motion analysis: Action detection, recognition and evaluation based on motion capture data.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容