ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

On Diversity in Image Captioning: Metrics and Methods

Wang, Qingzhong; Wan, Jia; Chan, Antoni B.*
IEEE Transactions on Pattern Analysis and Machine Intelligence2022-2-1DOI: 10.1109/TPAMI.2020.3013834
10被引9阅读
引用收藏
分享

摘要

Diversity is one of the most important properties in image captioning, as it reflects various expressions of important concepts presented in an image. However, the most popular metrics cannot well evaluate the diversity of multiple captions. In this paper, we first propose a metric to measure the diversity of a set of captions, which is derived from latent semantic analysis (LSA), and then kernelize LSA using CIDEr (R. Vedantam et al., 2015) similarity. Compared with mBLEU (R. Shetty et al., 2017), our proposed diversity metrics show a relatively strong correlation to human evaluation. We conduct extensive experiments, finding there is a large gap between the performance of the current state-of-the-art models and human annotations considering both diversity and accuracy; the models that aim to generate captions with higher CIDEr scores normally obtain lower diversity scores, which generally learn to describe images using common words. To bridge this "diversity" gap, we consider several methods for training caption models to generate diverse captions. First, we show that balancing the cross-entropy loss and CIDEr reward in reinforcement learning during training can effectively control the tradeoff between diversity and accuracy of the generated captions. Second, we develop approaches that directly optimize our diversity metric and CIDEr score using reinforcement learning. These proposed approaches using reinforcement learning (RL) can be unified into a self-critical (S. J. Rennie et al., 2017) framework with new RL baselines. Third, we combine accuracy and diversity into a single measure using an ensemble matrix, and then maximize the determinant of the ensemble matrix via reinforcement learning to boost diversity and accuracy, which outperforms its counterparts on the oracle test. Finally, inspired by determinantal point processes (DPP), we develop a DPP selection algorithm to select a subset of captions from a large number of candidate captions. The experimental results show that maximizing the determinant of the ensemble matrix outperforms other methods considerably improving diversity and accuracy.

学科与关键词

关键词
MeasurementSemanticsLearning (artificial intelligence)VegetationLegged locomotionTrainingComputational modelingImage captioningdiverse captionsreinforcement learningpolicy gradientadversarial trainingdiversity metric
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
IEEE Transactions on Pattern Analysis and Machine Intelligence
发表日期
2022-02-01
卷期
第 44 卷, 第 2 期
页码
1035-1049
DOI
10.1109/TPAMI.2020.3013834
语言
ENGLISH
期刊等级
1区
成果收录
SCIE
资助标注
City University of Hong Kong [7004682, 7005218]; NVIDIA Corporation

作者

  • W

    Wang, Qingzhong (第一作者)

  • W

    Wan, Jia

查看全部 3 位作者收起作者
  • C

    Chan, Antoni B. (通讯)

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417