《Knowledge Aided Consistency for Weakly Supervised Phrase Grounding》论文笔记

本文探讨了在弱监督phrase grounding任务中,如何利用视觉和语言模型的关联以及外部知识来提升性能。提出了KAC Net,通过知识辅助一致性网络和基于知识的池化门,关注与query相关的图像区域,以提高视觉和语言的一致性,从而在Flickr30K Entities和Referit Game数据集上取得显著改进。
摘要由CSDN通过智能技术生成

目录

abstract

introduction


abstract

  • phrase grounding:给出一张图片和一个自然语言描述的问题,在图片中定位问题中所提到的物体。是很多问题的基础(如 image retrieval、image QA 和 video QA)。
  • 在弱监督的场景中,图像区域 image regions(如proposals)和语言之间的映射在训练集中不存在。之前有方法通过在对predicted proposals 的 input queries 中获得的学习语言重建信息训练一个grounding system来解决这个问题。但这种优化仅仅是由语言模型的重建损失指导的,忽视了在proposals中的丰富的视觉信息及其他知识。

本文中,我们探讨了视觉和语言模型的关联,并利用互补的外部知识来促进弱监督grounding。我们提出了知识辅助一致性网络(Knowledge Aided Consistency Network,KAC Net)。为了利用在视觉特征中存在的互补知识,使用基于知识的池化(Knowledge Based Pooling,KBP)门来关注query-related proposals。


introduction

  • 使用传统方法来训练一个phrase grounding系统需要大量的人工标注来指示输入查询与所提到的图像中对象之间的映射,浪费时间且人为因素不准确。从而引出了半监督的方法。
  • 为了找到视觉和语言模型的关联,proposal generation sysgtem根据输入的图片产生一组候
Intelligent Reflecting Surface (IRS) is a new promising technology that can enhance the performance of cognitive radio (CR) networks by improving the spectrum sensing and communication efficiency. In this paper, we propose an IRS-aided spectrum sensing scheme for CR networks. The proposed scheme utilizes the passive reflecting property of IRS to enhance the signal-to-noise ratio (SNR) of the received signal at the CR receiver. The IRS reflects the received signal to enhance the received power and reduce the interference from other users in the network. The proposed scheme also uses machine learning techniques to adaptively adjust the reflecting coefficients of the IRS to maximize the SNR of the received signal. Simulation results show that the proposed scheme outperforms the conventional spectrum sensing scheme in terms of detection probability and false alarm rate. The simulation results also show that the proposed scheme can achieve a higher SNR with fewer samples than the conventional scheme. Moreover, the proposed scheme can improve the communication efficiency of the CR network by reducing the interference from other users in the network. In conclusion, the proposed IRS-aided spectrum sensing scheme can significantly enhance the performance of CR networks. The scheme can improve the spectrum sensing accuracy and communication efficiency by utilizing the passive reflecting property of IRS and the machine learning techniques to adaptively adjust the reflecting coefficients of the IRS. The proposed scheme has great potential in future CR networks to address the increasing demand for spectrum resources.
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值