Decoupled Global-Local Collaborative Network for Visual Question Answering.

Saved in:

Bibliographic Details
Title:	Decoupled Global-Local Collaborative Network for Visual Question Answering.
Authors:	Zhou, Ganlong¹ ganlongzhou@163.com, Han, Dezhi¹ dzhan@shmtu.edu.cn, Shen, Xiang^1,2 xiang.shen@sydney.edu.au, Xin, Xiaoqi¹
Source:	Computer Science & Information Systems. Sep2026, Vol. 23 Issue 4, p1259-1286. 28p.
Subjects:	Visual discrimination
Abstract:	Visual Question Answering (VQA) aims to achieve cross-modal semantic understanding through joint modeling of visual content and natural language. Although existing attention-based approaches effectively align features, they struggle to simultaneously accommodate global semantic modeling and local fine-grained perception within single-path architectures, leading to semantic drift and underutilization of information when addressing multi-perspective reasoning tasks. To mitigate this limitation, we propose a Decoupled Global-Local Collaborative Network (DGL-Net) that structurally partitions the cross-modal reasoning process into two complementary branches: global semantic understanding and local fine-grained modeling. Specifically, the global branch employs hierarchical attention fusion to model long-range dependencies and holistic scene semantics, providing contextual constraints for reasoning. The local branch introduces semantic relation enhancement and relevant region screening to explicitly model intra-modal structural relationships, strengthening fine-grained region-word alignment by injecting structural information. During training and inference, a branch-decoupling and collaborative fusion strategy enables independent yet complementary feature learning. Extensive experimental results demonstrate accuracies of 72.15% and 57.87% on VQA-v2 and GQA benchmarks, respectively. Notably, the proposed method exhibits enhanced robustness and generalization in complex semantic and compositional reasoning tasks, validating the efficacy of the decoupled collaborative strategy. [ABSTRACT FROM AUTHOR]
	Copyright of Computer Science & Information Systems is the property of ComSIS Consortium and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Visual Question Answering (VQA) aims to achieve cross-modal semantic understanding through joint modeling of visual content and natural language. Although existing attention-based approaches effectively align features, they struggle to simultaneously accommodate global semantic modeling and local fine-grained perception within single-path architectures, leading to semantic drift and underutilization of information when addressing multi-perspective reasoning tasks. To mitigate this limitation, we propose a Decoupled Global-Local Collaborative Network (DGL-Net) that structurally partitions the cross-modal reasoning process into two complementary branches: global semantic understanding and local fine-grained modeling. Specifically, the global branch employs hierarchical attention fusion to model long-range dependencies and holistic scene semantics, providing contextual constraints for reasoning. The local branch introduces semantic relation enhancement and relevant region screening to explicitly model intra-modal structural relationships, strengthening fine-grained region-word alignment by injecting structural information. During training and inference, a branch-decoupling and collaborative fusion strategy enables independent yet complementary feature learning. Extensive experimental results demonstrate accuracies of 72.15% and 57.87% on VQA-v2 and GQA benchmarks, respectively. Notably, the proposed method exhibits enhanced robustness and generalization in complex semantic and compositional reasoning tasks, validating the efficacy of the decoupled collaborative strategy. [ABSTRACT FROM AUTHOR]
ISSN:	18200214
DOI:	10.2298/CSIS260403039Z