Saved in:
Bibliographic Details
Main Authors: Luo, Jiamin, Zhao, Jianing, Wang, Jingjing, Zhou, Guodong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.19116
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916145636835328
author Luo, Jiamin
Zhao, Jianing
Wang, Jingjing
Zhou, Guodong
author_facet Luo, Jiamin
Zhao, Jianing
Wang, Jingjing
Zhou, Guodong
contents Weakly-supervised Phrase Grounding (WPG) is an emerging task of inferring the fine-grained phrase-region matching, while merely leveraging the coarse-grained sentence-image pairs for training. However, existing studies on WPG largely ignore the implicit phrase-region matching relations, which are crucial for evaluating the capability of models in understanding the deep multimodal semantics. To this end, this paper proposes an Implicit-Enhanced Causal Inference (IECI) approach to address the challenges of modeling the implicit relations and highlighting them beyond the explicit. Specifically, this approach leverages both the intervention and counterfactual techniques to tackle the above two challenges respectively. Furthermore, a high-quality implicit-enhanced dataset is annotated to evaluate IECI and detailed evaluations show the great advantages of IECI over the state-of-the-art baselines. Particularly, we observe an interesting finding that IECI outperforms the advanced multimodal LLMs by a large margin on this implicit-enhanced dataset, which may facilitate more research to evaluate the multimodal LLMs in this direction.
format Preprint
id arxiv_https___arxiv_org_abs_2402_19116
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle How to Understand "Support"? An Implicit-enhanced Causal Inference Approach for Weakly-supervised Phrase Grounding
Luo, Jiamin
Zhao, Jianing
Wang, Jingjing
Zhou, Guodong
Computation and Language
Artificial Intelligence
Weakly-supervised Phrase Grounding (WPG) is an emerging task of inferring the fine-grained phrase-region matching, while merely leveraging the coarse-grained sentence-image pairs for training. However, existing studies on WPG largely ignore the implicit phrase-region matching relations, which are crucial for evaluating the capability of models in understanding the deep multimodal semantics. To this end, this paper proposes an Implicit-Enhanced Causal Inference (IECI) approach to address the challenges of modeling the implicit relations and highlighting them beyond the explicit. Specifically, this approach leverages both the intervention and counterfactual techniques to tackle the above two challenges respectively. Furthermore, a high-quality implicit-enhanced dataset is annotated to evaluate IECI and detailed evaluations show the great advantages of IECI over the state-of-the-art baselines. Particularly, we observe an interesting finding that IECI outperforms the advanced multimodal LLMs by a large margin on this implicit-enhanced dataset, which may facilitate more research to evaluate the multimodal LLMs in this direction.
title How to Understand "Support"? An Implicit-enhanced Causal Inference Approach for Weakly-supervised Phrase Grounding
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2402.19116