用专家模型混合提升目标检测性能与可解释性
Domain-Specialized Object Detection via Model-Level Mixtures of Experts
- 将不同领域数据训练的YOLO专家模型通过门控网络动态组合
- 在BDD100K上优于传统集成方法，且避免专家坍缩
- 适合需要可解释性与领域适配的检测场景
混合专家（MoE）模型通过结构化整合专用神经网络，相比传统集成更具可解释性。尽管在图像分类和语义分割中取得成功，其在目标检测中的应用受限于密集且结构化的预测融合难题。本文研究了基于模型级混合专家的目标检测架构，提出一种结合在语义不交数据子集上训练的YOLO检测器的MoE结构，并引入学习型门控网络动态加权专家输出。我们探讨了多种检测结果融合策略及门控机制训练方法，包括采用平衡损失防止专家坍缩。在BDD100K数据集上的实验表明，该方法持续优于标准集成方案，并揭示了专家在不同领域间的专业化特征，证明模型级MoE是目标检测中传统集成的有效替代方案。代码已开源。
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。