面向领域泛化变化检测的视觉问答文本条件状态空间模型

Text-conditioned State Space Model For Domain-generalized Change Detection Visual Question Answering

August 12, 2025

作者: Elman Ghazaei, Erchan Aptoula

cs.AI

摘要

地球表面持续变化，探测这些变化为人类社会诸多领域提供了宝贵的洞见。尽管传统的变化检测方法已被用于从双时相图像中识别变化，但这些方法通常需要专业知识才能准确解读。为了让非专业用户更广泛、更灵活地获取变化信息，变化检测视觉问答（CDVQA）任务应运而生。然而，现有的CDVQA方法均建立在训练与测试数据集分布相似的假设之上，这一假设在现实应用中往往不成立，因为领域偏移频繁发生。本文重新审视CDVQA任务，着重解决领域偏移问题。为此，引入了一个新的多模态、多领域数据集——BrightVQA，以促进CDVQA领域泛化研究。此外，提出了一种新颖的状态空间模型，称为文本条件状态空间模型（TCSSM）。TCSSM框架旨在统一利用双时相图像与地理灾害相关文本信息，跨领域提取领域不变特征。TCSSM中存在的输入依赖参数通过双时相图像和地理灾害描述动态预测，从而促进双时相视觉数据与相关文本描述之间的对齐。通过大量实验，将所提方法与现有最先进模型进行对比评估，均展现出优越性能。代码与数据集将在论文被接受后公开于https://github.com/Elman295/TCSSM。

English

The Earth's surface is constantly changing, and detecting these changes provides valuable insights that benefit various aspects of human society. While traditional change detection methods have been employed to detect changes from bi-temporal images, these approaches typically require expert knowledge for accurate interpretation. To enable broader and more flexible access to change information by non-expert users, the task of Change Detection Visual Question Answering (CDVQA) has been introduced. However, existing CDVQA methods have been developed under the assumption that training and testing datasets share similar distributions. This assumption does not hold in real-world applications, where domain shifts often occur. In this paper, the CDVQA task is revisited with a focus on addressing domain shift. To this end, a new multi-modal and multi-domain dataset, BrightVQA, is introduced to facilitate domain generalization research in CDVQA. Furthermore, a novel state space model, termed Text-Conditioned State Space Model (TCSSM), is proposed. The TCSSM framework is designed to leverage both bi-temporal imagery and geo-disaster-related textual information in an unified manner to extract domain-invariant features across domains. Input-dependent parameters existing in TCSSM are dynamically predicted by using both bi-temporal images and geo-disaster-related description, thereby facilitating the alignment between bi-temporal visual data and the associated textual descriptions. Extensive experiments are conducted to evaluate the proposed method against state-of-the-art models, and superior performance is consistently demonstrated. The code and dataset will be made publicly available upon acceptance at https://github.com/Elman295/TCSSM.