arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.09151cs.CVcs.CLcs.LG
收藏

基于记忆注意的群体区分图像描述

Group-based Distinctive Image Captioning with Memory Attention

City University of Hong Kong(香港城市大学);Aerospace Information Research Institute, Chinese Academy of Sciences(中国科学院空天信息创新研究院);University of Chinese Academy of Sciences(中国科学院大学);Baidu Research(百度研究院)

Jiuniu Wang, Wenjia Xu, Qingzhong Wang, Antoni B. Chan

摘要:

使用自然语言描述图像被广泛称为图像描述,由于计算机视觉和自然语言生成技术的发展,其取得了一致的进展。虽然传统的字幕模型基于流行的度量实现了高准确性,即,BLEU、CIDEr和SPICE,字幕区分目标图像与其他类似图像的能力尚未得到充分开发。为了生成独特的字幕,一些先驱者采用了对比学习或重新加权地面实况字幕,专注于一个单一的输入图像。然而,相似图像组中的对象之间的关系(例如,同一相册内的项目或属性或细粒度事件)被忽略。在本文中,我们使用基于组的区别性字幕模型(GdisCap),将每个图像与一个相似组中的其他图像进行比较,突出每个图像的独特性,从而提高图像字幕的区别性。特别地,我们提出了基于组的记忆注意力(GMA)模块,其存储在图像组中唯一的对象特征(即,与其它图像中的对象具有低相似性)。这些独特的对象特征在生成字幕时被突出显示,从而产生更独特的字幕。此外,地面实况字幕中的独特的词被选择来监督语言解码器和GMA。最后,我们提出了一个新的评价指标,独特的字率(DisWordRate)来衡量字幕的独特性。定量结果表明,该方法显著提高了多个基线模型的区分度,在准确性和区分度上均达到了最先进水平。用户研究的结果与定量评估一致,并证明了新的度量DisWordRate的合理性。

英文摘要:

Describing images using natural language is widely known as image captioning, which has made consistent progress due to the development of computer vision and natural language generation techniques. Though conventional captioning models achieve high accuracy based on popular metrics, i.e., BLEU, CIDEr, and SPICE, the ability of captions to distinguish the target image from other similar images is under-explored. To generate distinctive captions, a few pioneers employ contrastive learning or re-weighted the ground-truth captions, which focuses on one single input image. However, the relationships between objects in a similar image group (e.g., items or properties within the same album or fine-grained events) are neglected. In this paper, we improve the distinctiveness of image captions using a Group-based Distinctive Captioning Model (GdisCap), which compares each image with other images in one similar group and highlights the uniqueness of each image. In particular, we propose a group-based memory attention (GMA) module, which stores object features that are unique among the image group (i.e., with low similarity to objects in other images). These unique object features are highlighted when generating captions, resulting in more distinctive captions. Furthermore, the distinctive words in the ground-truth captions are selected to supervise the language decoder and GMA. Finally, we propose a new evaluation metric, distinctive word rate (DisWordRate) to measure the distinctiveness of captions. Quantitative results indicate that the proposed method significantly improves the distinctiveness of several baseline models, and achieves the state-of-the-art performance on both accuracy and distinctiveness. Results of a user study agree with the quantitative evaluation and demonstrate the rationality of the new metric DisWordRate.

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。

↑