AMEND：一种用于长尾轨迹预测的混合专家框架
AMEND: A Mixture of Experts Framework for Long-tailed Trajectory Prediction
AI总结：
针对轨迹预测数据集的长尾效应问题，提出一种模块化、模型无关的混合专家框架，通过路由网络选择最佳专家生成预测，有效提升了模型在长尾安全关键场景下的性能。
摘要：
准确预测行人的未来运动对智能驾驶系统至关重要。开发用于此任务的模型需要包含多样化样本的丰富数据集。然而，现有的自然轨迹预测数据集通常偏向于简单样本，缺乏具有挑战性的场景。这种长尾效应导致预测模型在包含安全关键场景的数据分布尾部表现不佳。先前的方法使用对比学习和类条件超网络等方法来解决长尾问题。然而，这些方法不是模块化的，无法应用于许多机器学习架构。在这项工作中，我们提出了一个模块化的、模型无关的轨迹预测框架，该框架利用了专门的混合专家。在我们的方法中，每个专家针对数据的特定部分进行专门技能的训练。为了生成预测，我们利用路由网络通过生成相对置信度分数来选择最佳专家。我们在常见的行人轨迹预测数据集上进行了实验，并表明我们的方法提高了在长尾场景下的性能。我们进一步进行了消融研究，以突出不同提出组件的贡献。
英文摘要：
Accurate prediction of pedestrians' future motions is critical for intelligent driving systems. Developing models for this task requires rich datasets containing diverse sets of samples. However, the existing naturalistic trajectory prediction datasets are generally imbalanced in favor of simpler samples and lack challenging scenarios. Such a long-tail effect causes prediction models to underperform on the tail portion of the data distribution containing safety-critical scenarios. Previous methods tackle the long-tail problem using methods such as contrastive learning and class-conditioned hypernetworks. These approaches, however, are not modular and cannot be applied to many machine learning architectures. In this work, we propose a modular model-agnostic framework for trajectory prediction that leverages a specialized mixture of experts. In our approach, each expert is trained with a specialized skill with respect to a particular part of the data. To produce predictions, we utilise a router network that selects the best expert by generating relative confidence scores. We conduct experimentation on common pedestrian trajectory prediction datasets and show that our method improves performance on long-tail scenarios. We further conduct ablation studies to highlight the contribution of different proposed components.
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。
