arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.01338cs.CVcs.CL
收藏

学习为图像描述搭配视觉-语言神经模块

Learning to Collocate Visual-Linguistic Neural Modules for Image Captioning

Southeast University(东南大学);Nanyang Technological University(南洋理工大学);Northwestern University(西北大学);Monash University(莫纳什大学)

Xu Yang, Hanwang Zhang, Chongyang Gao, Jianfei Cai

AI总结:

本文提出CVLNM图像描述器,通过可区分的视觉-语言模块、自注意力控制器和词性句法损失实现动态模块搭配,并在MS-COCO上取得129.5 CIDEr-D的最优性能。

摘要:

人类倾向于将句子分解为不同部分,例如“某物在某处做某事”,然后用特定内容填充每个部分。受此启发,我们遵循模块化设计原则,提出了一种新颖的图像描述器:学习搭配视觉-语言神经模块(CVLNM)。不同于视觉问答(VQA)中广泛使用的神经模块网络——在那里语言(即问题)是完全可观察的——搭配视觉-语言模块的任务更具挑战性。这是因为语言仅部分可观察,因此我们需要在图像描述过程中动态地搭配模块。总之,我们在设计和训练CVLNM方面做出了以下技术贡献:1)可区分的模块设计——编码器中的四个模块,包括一个用于功能词的语言模块和三个用于不同实词(即名词、形容词和动词)的视觉模块,以及解码器中另一个用于常识推理的语言模块;2)一个基于自注意力的模块控制器,用于增强视觉推理的鲁棒性;3)施加在模块控制器上的基于词性的句法损失,以进一步正则化CVLNM的训练。在MS-COCO数据集上的大量实验表明,我们的CVLNM更加有效,例如取得了新的最先进水平129.5 CIDEr-D,并且更加鲁棒,例如更不容易过拟合数据集偏差,并且在可用训练样本较少时性能下降更小。代码可在https://github.com/GCYZSL/CVLMN获取。

英文摘要:

Humans tend to decompose a sentence into different parts like \textsc{sth do sth at someplace} and then fill each part with certain content. Inspired by this, we follow the \textit{principle of modular design} to propose a novel image captioner: learning to Collocate Visual-Linguistic Neural Modules (CVLNM). Unlike the \re{widely used} neural module networks in VQA, where the language (\ie, question) is fully observable, \re{the task of collocating visual-linguistic modules is more challenging.} This is because the language is only partially observable, for which we need to dynamically collocate the modules during the process of image captioning. To sum up, we make the following technical contributions to design and train our CVLNM: 1) \textit{distinguishable module design} -- \re{four modules in the encoder} including one linguistic module for function words and three visual modules for different content words (\ie, noun, adjective, and verb) and another linguistic one in the decoder for commonsense reasoning, 2) a self-attention based \textit{module controller} for robustifying the visual reasoning, 3) a part-of-speech based \textit{syntax loss} imposed on the module controller for further regularizing the training of our CVLNM. Extensive experiments on the MS-COCO dataset show that our CVLNM is more effective, \eg, achieving a new state-of-the-art 129.5 CIDEr-D, and more robust, \eg, being less likely to overfit to dataset bias and suffering less when fewer training samples are available. Codes are available at \url{https://github.com/GCYZSL/CVLMN}

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。

↑