诊断视觉和语言导航：真正重要的是什么
Diagnosing Vision-and-Language Navigation: What Really Matters
摘要：
视觉和语言导航（VLN）是一种多模态任务，其中智能体遵循自然语言指令并在视觉环境中导航。已经提出了多种设置，研究人员应用新的模型架构或训练技术来提高导航性能。然而，机器的性能和人类基准之间仍然存在不可忽视的差距。此外，智能体的内部导航决策机制仍然不清楚。据我们所知，代理人如何感知多模态输入是研究不足，需要调查。在这项工作中，我们进行了一系列的诊断实验，以揭示代理的重点在导航。结果表明，室内导航代理参考对象和方向令牌时，作出决定。相比之下，户外导航代理严重依赖于方向令牌和理解对象令牌差。基于transformer的代理获得了更好的跨模态的理解对象，并显示出强大的数值推理能力比非transformer的代理。当涉及到视觉和语言对齐时，许多模型声称它们可以将对象标记与特定的视觉目标对齐。我们发现不平衡的视觉和文本输入的注意力和怀疑这种跨通道对齐的可靠性。
英文摘要：
Vision-and-language navigation (VLN) is a multimodal task where an agent follows natural language instructions and navigates in visual environments. Multiple setups have been proposed, and researchers apply new model architectures or training techniques to boost navigation performance. However, there still exist non-negligible gaps between machines' performance and human benchmarks. Moreover, the agents' inner mechanisms for navigation decisions remain unclear. To the best of our knowledge, how the agents perceive the multimodal input is under-studied and needs investigation. In this work, we conduct a series of diagnostic experiments to unveil agents' focus during navigation. Results show that indoor navigation agents refer to both object and direction tokens when making decisions. In contrast, outdoor navigation agents heavily rely on direction tokens and poorly understand the object tokens. Transformer-based agents acquire a better cross-modal understanding of objects and display strong numerical reasoning ability than non-Transformer-based agents. When it comes to vision-and-language alignments, many models claim that they can align object tokens with specific visual targets. We find unbalanced attention on the vision and text input and doubt the reliability of such cross-modal alignments.
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。
