Abstract
The workflow of extracting features from images using convolutional neural networks (CNN) and generating captions with recurrent neural networks (RNN) has become a de-facto standard for image captioning task. However, since CNN features are originally designed for classification task, it is mostly concerned with the main conspicuous element of the image, and often fails to correctly convey information on local, secondary elements. We propose to incorporate coding with vector of locally aggregated descriptors (VLAD) on spatial pyramid for CNN features of sub-regions in order to generate image representations that better reflect the local information of the images. Our results show that our method of compact VLAD coding can match CNN features with as little as 3% of dimensionality and, when combined with spatial pyramid, it results in image captions that more accurately take local elements into account.
Abstract (translated by Google)
使用卷积神经网络（CNN）从图像中提取特征并使用递归神经网络（RNN）生成字幕的工作流已经成为图像字幕任务的事实上的标准。但是，由于CNN特征本来就是为分类任务设计的，因此主要关注图像的主要显着元素，而往往不能正确传达本地，次要元素的信息。为了生成更好地反映图像局部信息的图像表示，我们提出将编码与空间金字塔上的局部聚合描述符（VLAD）矢量合并为子区域的CNN特征。我们的结果表明，我们的紧凑型VLAD编码方法可以将CNN特征与维度的3％进行匹配，并且当与空间金字塔结合时，会导致图像标题更加准确地考虑到局部元素。
URL
https://arxiv.org/abs/1603.09046