arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.02772cs.CVcs.CLcs.MM
收藏

视觉语言预训练模型在监督式跨模态检索中的综合实证研究

A Comprehensive Empirical Study of Vision-Language Pre-trained Model for Supervised Cross-Modal Retrieval

Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)

Zhixiong Zeng, Wenji Mao

摘要:

跨模态检索(Cross-Modal Retrieval,CMR)是一个跨多模态计算和信息检索的重要研究课题,它以一种类型的数据作为查询,检索另一种类型的相关数据。它已被广泛应用于许多实际应用中。最近,以CLIP为代表的视觉语言预训练模型在学习视觉和文本表示方面表现出了优越性,并在各种视觉和语言相关任务中获得了令人印象深刻的性能。尽管CLIP和以前的预训练模型在无监督CMR中表现出很大的性能改进,但由于缺乏多模态类级关联的共同表示,这些预训练模型对监督CMR的性能和影响很少被探索。本文以CLIP作为当前具有代表性的视觉语言预训练模型进行了全面的实证研究。我们评估其性能和影响的监督CMR,并试图回答几个关键的研究问题。为此,我们首先提出了一种新的模型CLIP 4CMR(CLIP增强网络跨模态检索),采用预训练的CLIP作为骨干网络执行监督CMR。然后,通过CLIP 4CMR框架,我们重新审视现有CMR方法中不同学习目标的设计,为模型设计提供新的见解。此外,我们还研究了CMR应用中最受关注的方面,包括对模态不平衡的鲁棒性和对超参数的敏感性,为实际应用提供了新的视角。通过大量的实验,我们表明,CLIP 4CMR实现了SOTA的结果与基准数据集的显着改善,并可以作为一个基本框架,实证研究的关键研究问题的监督CMR,具有重要意义的模型设计和实际考虑。

英文摘要:

Cross-Modal Retrieval (CMR) is an important research topic across multimodal computing and information retrieval, which takes one type of data as the query to retrieve relevant data of another type. It has been widely used in many real-world applications. Recently, the vision-language pre-trained models represented by CLIP demonstrate its superiority in learning the visual and textual representations and gain impressive performance on various vision and language related tasks. Although CLIP as well as the previous pre-trained models have shown great performance improvement in the unsupervised CMR, the performance and impact of these pre-trained models on the supervised CMR were rarely explored due to the lack of common representation for the multimodal class-level associations. In this paper, we take CLIP as the current representative vision-language pre-trained model to conduct a comprehensive empirical study. We evaluate its performance and impact on the supervised CMR, and attempt to answer several key research questions. To this end, we first propose a novel model CLIP4CMR (CLIP enhanced network for Cross-Modal Retrieval) that employs the pre-trained CLIP as backbone network to perform the supervised CMR. Then by means of the CLIP4CMR framework, we revisit the design of different learning objectives in current CMR methods to provide new insights on model design. Moreover, we investigate the most concerned aspects in applying CMR, including the robustness to modality imbalance and sensitivity to hyper-parameters, to provide new perspectives for practical applications. Through extensive experiments, we show that CLIP4CMR achieves the SOTA results with prominent improvements on the benchmark datasets, and can be used as a fundamental framework to empirically study the key research issues of the supervised CMR, with significant implications for model design and practical considerations.

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。

↑