Pretrained Vision-Language Models (VLMs) have achieved remarkable performance in image retrieval from text. However, their performance drops drastically when confronted with linguistically complex texts that they struggle to comprehend. Inspired by the Divide-and-Conquer algorithm and dual-process theory, in this paper, we regard linguistically complex texts as compound proposition texts composed of multiple simple proposition sentences and propose an end-to-end Neural Divide-and-Conquer Reasoning framework, dubbed NDCR. It contains three main components: 1)Divide: a proposition generator divides the compound proposition text into simple proposition sentences and produces their corresponding representations, 2)Conquer: a pretrained VLMs-based visual-linguistic interactor achieves the interaction between decomposed proposition sentences and images, 3)Combine: a neural-symbolic reasoner combines the above reasoning states to obtain the final solution via a neural logic reasoning approach. According to the dual-process theory, the visual-linguistic interactor and neural-symbolic reasoner could be regarded as analogical reasoning System 1 and logical reasoning System 2. We conduct extensive experiments on a challenging image retrieval from contextual descriptions data set. Experimental results and analyses indicate NDCR significantly improves performance in the complex image-text reasoning problem. Code link: https://github.com/YunxinLi/NDCR.

翻译：预训练的视觉-语言模型（Vision-Language Models, VLMs）在基于文本的图像检索任务中取得了显著性能。然而，当面对难以理解的语言复杂文本时，其性能会急剧下降。受分治算法和双过程理论启发，本文将语言复杂文本视为由多个简单命题语句组成的复合命题文本，并提出一种端到端的神经分治推理框架（Neural Divide-and-Conquer Reasoning, NDCR）。该框架包含三个主要组件：1）分治：命题生成器将复合命题文本分解为简单命题语句，并生成其对应表示；2）征服：基于预训练VLM的视觉-语言交互器实现分解后的命题语句与图像间的交互；3）组合：神经符号推理器通过神经逻辑推理方法整合上述推理状态以获取最终解。根据双过程理论，视觉-语言交互器和神经符号推理器可分别类比为类比推理系统1和逻辑推理系统2。我们在具有挑战性的上下文描述图像检索数据集上进行了广泛实验。实验结果与分析表明，NDCR在复杂图像-文本推理问题上显著提升了性能。代码链接：https://github.com/YunxinLi/NDCR。