arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.09742cs.CV
收藏

AutoCaption:基于神经结构搜索的图像描述

AutoCaption: Image Captioning with Neural Architecture Search

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)

Xinxin Zhu, Weining Wang, Longteng Guo, Jing Liu

摘要:

图像描述将复杂的视觉信息转化为抽象的自然语言进行表示,可以帮助计算机快速理解世界。但由于现实环境的复杂性,它需要识别关键对象并实现它们之间的联系,进而生成自然语言。整个过程涉及一个视觉理解模块和一个语言生成模块,这给深度神经网络的设计带来了比其他任务更多的挑战。神经结构搜索(NAS)在各种图像识别任务中显示出其重要作用。此外,RNN在图像描述任务中起着至关重要的作用。为了更好地设计图像描述的解码器模块,我们引入了AutoCaption方法,使用NAS自动设计解码器模块AutoRNN。我们使用基于共享参数的强化学习方法来有效地自动设计AutoRNN。AutoCaption的搜索空间包含了层间的连接和层内的操作,使得AutoRNN可以表达更多的结构。特别地,RNN等价于我们的搜索空间的子集。在MSCOCO数据集上的实验表明,我们的AutoCaption模型可以获得比传统手工设计方法更好的性能。

英文摘要:

Image captioning transforms complex visual information into abstract natural language for representation, which can help computers understanding the world quickly. However, due to the complexity of the real environment, it needs to identify key objects and realize their connections, and further generate natural language. The whole process involves a visual understanding module and a language generation module, which brings more challenges to the design of deep neural networks than other tasks. Neural Architecture Search (NAS) has shown its important role in a variety of image recognition tasks. Besides, RNN plays an essential role in the image captioning task. We introduce a AutoCaption method to better design the decoder module of the image captioning where we use the NAS to design the decoder module called AutoRNN automatically. We use the reinforcement learning method based on shared parameters for automatic design the AutoRNN efficiently. The search space of the AutoCaption includes connections between the layers and the operations in layers both, and it can make AutoRNN express more architectures. In particular, RNN is equivalent to a subset of our search space. Experiments on the MSCOCO datasets show that our AutoCaption model can achieve better performance than traditional hand-design methods.

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。

↑