arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.13623cs.CVcs.CL
收藏

用于图像描述的交互式机器学习

Interactive Machine Learning for Image Captioning

German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心);Oldenburg University(奥尔登堡大学)

Mareike Hartmann, Aliki Anagnostopoulou, Daniel Sonntag

摘要:

我们提出了一种交互式学习的图像描述模型的方法。由于人的反馈是昂贵的,现代神经网络的方法往往需要大量的监督数据进行训练,我们设想一个系统,利用人的反馈,尽可能好地利用反馈使用数据增强的方法,并集成所产生的训练样本到模型中的智能方式。这种方法有三个关键组成部分,我们需要找到合适的实际实现:反馈收集,数据增强和模型更新。我们概述了我们的想法,并审查了解决这些任务的不同可能性。

英文摘要:

We propose an approach for interactive learning for an image captioning model. As human feedback is expensive and modern neural network based approaches often require large amounts of supervised data to be trained, we envision a system that exploits human feedback as good as possible by multiplying the feedback using data augmentation methods, and integrating the resulting training examples into the model in a smart way. This approach has three key components, for which we need to find suitable practical implementations: feedback collection, data augmentation, and model update. We outline our idea and review different possibilities to address these tasks.

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。

↑