A Lightweight and Effective Multi-View Knowledge Distillation Framework for Text-Image Retrieval

Author:

Song Yuxiang1,Zheng Yuxuan1,Zhao Shangqing1,Liu Shu1,Zhuang Xinlin1,Long Zhaoguang1,Sun Changzhi1,Zhou Aimin1,Lan Man1

Affiliation:

1. East China Normal University,School of Computer Science and Technology,Shanghai,China

Funder

National Natural Science Foundation of China

Technology Development

Science and Technology Commission of Shanghai Municipality

East China Normal University

Publisher

IEEE

Reference39 articles.

1. Rethinking Benchmarks for Cross-modal Image-text Retrieval

2. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation;Li

3. Align before fuse: Vision and language representation learning with momentum distillation;Li;Advances in neural information processing systems,2021

4. Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework;Wang

5. AGREE: Aligning Cross-Modal Entities for Image-Text Retrieval Upon Vision-Language Pre-trained Models

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3