BetterCheck：迈向汽车感知系统中 VLM 的安全防护
BetterCheck: Towards Safeguarding VLMs for Automotive Perception Systems
AI总结：
针对 VLM 在汽车感知中可能漏检或虚构交通参与者的问题，本文基于 Waymo Open Dataset 评估 3 个先进 VLM，并提出幻觉检测框架 BetterCheck 以构建安全防护。
摘要：
大语言模型（LLM）正越来越多地被扩展用于同时处理文本和视频等多模态数据。它们在理解图像内容方面的出色表现，正在超越 Yolo 等专用神经网络（NN）；后者仅支持结构良好但非常有限的词汇表，即其能够检测的对象。在不受限制的情况下，LLM，尤其是最先进的视觉语言模型（VLM），在描述甚至复杂交通状况时都表现出令人印象深刻的性能。这使其有可能成为汽车感知系统的合适组件，以支持对复杂交通状况或边缘案例状况的理解。然而，LLM 和 VLM 容易产生幻觉，这意味着它们可能看不到某一状况中实际存在的交通参与者，例如弱势道路使用者，或者看到现实中并不存在的交通参与者。后一种情况并不可取，会使高级驾驶辅助系统（ADAS）或自动驾驶系统（ADS）发生不必要的减速，而前一种情况则可能导致 ADS 作出灾难性决策。在本工作中，我们系统评估了 3 个最先进 VLM 在从 Waymo Open Dataset 采样的多样化交通状况子集上的性能，以支持安全防护栏，用于捕获由 VLM 支持的感知系统中的此类幻觉。我们观察到，专有和开放 VLM 都展现出显著的图像理解能力，甚至会细致关注有时人类难以察觉的细微细节。然而，迄今为止它们仍倾向于在描述中编造元素，因此需要幻觉检测策略，例如我们在本工作中提出的 BetterCheck。
英文摘要：
Large language models (LLMs) are growingly extended to process multimodal data such as text and video simultaneously. Their remarkable performance in understanding what is shown in images is surpassing specialized neural networks (NNs) such as Yolo that is supporting only a well-formed but very limited vocabulary, ie., objects that they are able to detect. When being non-restricted, LLMs and in particular state-of-the-art vision language models (VLMs) show impressive performance to describe even complex traffic situations. This is making them potentially suitable components for automotive perception systems to support the understanding of complex traffic situations or edge case situation. However, LLMs and VLMs are prone to hallucination, which mean to either potentially not seeing traffic agents such as vulnerable road users who are present in a situation, or to seeing traffic agents who are not there in reality. While the latter is unwanted making an ADAS or autonomous driving systems (ADS) to unnecessarily slow down, the former could lead to disastrous decisions from an ADS. In our work, we are systematically assessing the performance of 3 state-of-the-art VLMs on a diverse subset of traffic situations sampled from the Waymo Open Dataset to support safety guardrails for capturing such hallucinations in VLM-supported perception systems. We observe that both, proprietary and open VLMs exhibit remarkable image understanding capabilities even paying thorough attention to fine details sometimes difficult to spot for us humans. However, they are also still prone to making up elements in their descriptions to date requiring hallucination detection strategies such as BetterCheck that we propose in our work.
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。
