双重思维与逻辑处理——多模态大语言模型是否正在缩小与人类视觉的差距？
Dual Thinking and Logical Processing -- Are Multi-modal Large Language Models Closing the Gap with Human Vision ?
AI总结：
本研究通过对抗性数据集和心理物理学实验揭示人类视觉的双重思维，发现多模态大语言模型在逻辑处理上进步滞后于直觉处理，并强调整合逻辑处理能力对安全关键领域的重要性。
摘要：
双重思维框架考虑了快速、直觉性的处理以及较慢的逻辑处理。在视觉中感知双重思维需要那些直觉处理与逻辑处理推断结果不同的图像，而后者在当前研究中尚未得到充分探索。我们引入了一个新颖的对抗性数据集，为人类视觉中的双重思维框架提供证据，这也促进了深度学习模型定性行为的研究。我们的心理物理学研究表明，在快速连续中会存在多种推断，而错误分析显示，视觉处理的提前终止可能导致遗漏相关信息。多模态大语言模型（MLLMs）和视觉语言模型（VLMs）在纠正人类视觉中直觉处理的错误方面取得了显著进展，并在需要逻辑处理的图像上表现出增强的性能。然而，它们在逻辑处理上的改进并未跟上其在直觉处理上的进步。相比之下，分割模型表现出的错误类似于人类直觉处理中观察到的错误，并且缺乏对子结构的理解，这体现在识别实例中与子组件相关的错误上。随着基于人工智能（AI）的系统在自动驾驶等安全关键领域中的应用日益增多，整合逻辑处理能力变得至关重要。这不仅提升了性能，还解决了基于扩展方法的局限性，同时确保了在现实环境中的鲁棒性和可靠性。
英文摘要：
The dual thinking framework considers fast, intuitive, and slower logical processing. The perception of dual thinking in vision requires images where inferences from intuitive and logical processing differ, and the latter is under-explored in current studies. We introduce a novel adversarial dataset to provide evidence for the dual thinking framework in human vision, which also facilitates the study of the qualitative behavior of deep learning models. Our psychophysical studies show the presence of multiple inferences in rapid succession, and analysis of errors shows that the early stopping of visual processing can result in missing relevant information. MLLMs (Multi-modal Large Language Models) and VLMs (Vision Language Models) have made significant progress in correcting errors in intuitive processing in human vision and showed enhanced performance on images requiring logical processing. However, their improvements in logical processing have not kept pace with their advancements in intuitive processing. In contrast, segmentation models exhibit errors similar to those seen in intuitive human processing and lack understanding of sub-structures, as indicated by errors related to sub-components in identified instances. As AI (Artificial Intelligence)-based systems find increasing applications in safety-critical domains like autonomous driving, the integration of logical processing capabilities becomes essential. This not only enhances performance but also addresses the limitations of scaling-based approaches while ensuring robustness and reliability in real-world environments.
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。
