Abstract
In this paper, we exploit a memory-augmented neural network to predict accurate answers to visual questions, even when those answers occur rarely in the training set. The memory network incorporates both internal and external memory blocks and selectively pays attention to each training exemplar. We show that memory-augmented neural networks are able to maintain a relatively long-term memory of scarce training exemplars, which is important for visual question answering due to the heavy-tailed distribution of answers in a general VQA setting. Experimental results on two large-scale benchmark datasets show the favorable performance of the proposed algorithm with a comparison to state of the art.
Abstract (translated)
在本文中，我们利用记忆增强神经网络来预测视觉问题的准确答案，即使这些答案在训练集中很少发生。存储器网络包含内部和外部存储器块，并有选择地关注每个培训示例。我们表明，记忆增强神经网络能够保持稀缺训练样本的相对长期记忆，这对于视觉问题回答非常重要，这是由于在一般VQA环境中的重尾分布的答案。在两个大型基准数据集上的实验结果显示了所提出的算法与现有技术的比较的良好性能。
URL
https://arxiv.org/abs/1707.04968
