arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.00390cs.CVcs.CL
收藏

基于图文匹配模型的图像描述提取

More Grounded Image Captioning by Distilling Image-Text Matching Model

Hefei University of Technology(合肥工业大学);University of Science and Technology of China(中国科学技术大学);Nanyang Technological University(南洋理工大学)

Yuanen Zhou, Meng Wang, Daqing Liu, Zhenzhen Hu, Hanwang Zhang

摘要:

视觉注意力不仅可以提高图像字幕的性能,而且可以作为一种视觉解释来定性地衡量字幕的合理性和模型的透明度。具体来说,我们期望字幕者能够在生成相应单词的同时将其专注的目光固定在正确的对象上。这种能力也被称为接地图像描述。然而,现有字幕机的接地精度远不能令人满意。为了在保持字幕质量的同时提高接地精度,收集词区域对齐作为强监督是昂贵的。为此,我们提出了一个部分的语音(POS)增强的图像-文本匹配模型(SCAN \cite{lee2018stacked}):POS-SCAN,作为更接地图像描述的有效知识蒸馏。好处是双重的:1)给定一个句子和一幅图像,POS-SCAN可以比SCAN更准确地定位对象; 2)POS-SCAN作为字幕者视觉注意力模块的单词区域对齐正则化。通过展示基准实验结果,我们证明了配备POS-SCAN的传统图像字幕机可以在没有强有力监督的情况下显着提高接地精度。最后但并非最不重要的是,我们探讨了不可或缺的自我批判序列训练(SCST)\cite{Rennie_2017_CVPR}的背景下接地图像描述,并表明图像-文本匹配分数可以作为奖励更接地的字幕\footnote{https://github.com/YuanEZhou/Grounded-Image-Captioning}。

英文摘要:

Visual attention not only improves the performance of image captioners, but also serves as a visual interpretation to qualitatively measure the caption rationality and model transparency. Specifically, we expect that a captioner can fix its attentive gaze on the correct objects while generating the corresponding words. This ability is also known as grounded image captioning. However, the grounding accuracy of existing captioners is far from satisfactory. To improve the grounding accuracy while retaining the captioning quality, it is expensive to collect the word-region alignment as strong supervision. To this end, we propose a Part-of-Speech (POS) enhanced image-text matching model (SCAN \cite{lee2018stacked}): POS-SCAN, as the effective knowledge distillation for more grounded image captioning. The benefits are two-fold: 1) given a sentence and an image, POS-SCAN can ground the objects more accurately than SCAN; 2) POS-SCAN serves as a word-region alignment regularization for the captioner's visual attention module. By showing benchmark experimental results, we demonstrate that conventional image captioners equipped with POS-SCAN can significantly improve the grounding accuracy without strong supervision. Last but not the least, we explore the indispensable Self-Critical Sequence Training (SCST) \cite{Rennie_2017_CVPR} in the context of grounded image captioning and show that the image-text matching score can serve as a reward for more grounded captioning \footnote{https://github.com/YuanEZhou/Grounded-Image-Captioning}.

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。

↑