基于模型层面专家混合的对象检测
Domain-Specialized Object Detection via Model-Level Mixtures of Experts
AI总结：
本文提出一种基于模型层面专家混合的对象检测方法，通过结合不同数据集训练的YOLO检测器和动态加权的门控网络，提升检测性能和可解释性。
摘要：
混合专家（MoE）模型提供了一种结构化的方法来结合专门的神经网络，比传统集合更具可解释性。尽管MoEs已在图像分类和语义分割中成功应用，但其在目标检测中的应用受限于合并密集和结构化预测的挑战。本文研究了模型层面的专家混合，并分析其在提升目标检测性能和可解释性中的适用性。我们提出了一种MoE架构，结合在语义上不重叠的数据子集上训练的基于YOLO的检测器，并通过学习的门控网络动态加权专家贡献。我们研究了不同策略来融合检测输出和训练门控机制，包括平衡损失以防止专家崩溃。在BDD100K数据集上的实验表明，所提出的MoE在标准集合方法上表现更优，并提供了跨领域的专家专业化见解，突显了模型层面的MoEs作为传统集合的可行替代方案。我们的代码可在https://github.com/KASTEL-MobilityLab/mixtures-of-experts/上获取。
英文摘要：
Mixture-of-Experts (MoE) models provide a structured approach to combining specialized neural networks and offer greater interpretability than conventional ensembles. While MoEs have been successfully applied to image classification and semantic segmentation, their use in object detection remains limited due to challenges in merging dense and structured predictions. In this work, we investigate model-level mixtures of object detectors and analyze their suitability for improving performance and interpretability in object detection. We propose an MoE architecture that combines YOLO-based detectors trained on semantically disjoint data subsets, with a learned gating network that dynamically weights expert contributions. We study different strategies for fusing detection outputs and for training the gating mechanism, including balancing losses to prevent expert collapse. Experiments on the BDD100K dataset demonstrate that the proposed MoE consistently outperforms standard ensemble approaches and provides insights into expert specialization across domains, highlighting model-level MoEs as a viable alternative to traditional ensembling for object detection. Our code is available at https://github.com/KASTEL-MobilityLab/mixtures-of-experts/.
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。
