DAMEX: 面向混合数据集视觉理解的数据集感知混合专家模型
DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets
AI总结：
针对大规模混合数据集训练通用检测器参数量大的问题，提出数据集感知混合专家模型DAMEX，通过路由数据集令牌到对应专家实现数据集专属知识整合，在通用目标检测基准上显著超越现有最优方法及非MoE基线，且对专家表示崩溃鲁棒。
摘要：
构建通用检测器面临一个关键问题：我们如何才能最有效地在大规模混合数据集上训练模型？答案在于学习数据集专属特征并整合其知识，且所有这些都要在单个模型中完成。现有方法通过在公共主干网络上设置独立检测头来实现这一点，但这会导致参数量大幅增加。在本研究中，我们将混合专家（Mixture-of-Experts, MoE）作为解决方案，强调MoE远不止是一种可扩展性工具。我们提出了数据集感知混合专家模型DAMEX，在该模型中，我们通过学习将每个数据集的令牌路由到其映射的专家，来训练专家成为对应数据集的“专家”。在通用目标检测基准（Universal Object-Detection Benchmark）上的实验表明，我们的方法比现有最优方法的平均AP分数高出+10.2，且比我们的非MoE基线的平均AP分数提升了+2.0。我们还观察到，在混合以下三类数据集时均能获得一致的性能提升：（1）可用数据有限的数据集；（2）领域差异大的数据集；（3）标签集差异大的数据集。此外，我们通过定性分析证明DAMEX对专家表示崩溃具有鲁棒性。
英文摘要：
Construction of a universal detector poses a crucial question: How can we most effectively train a model on a large mixture of datasets? The answer lies in learning dataset-specific features and ensembling their knowledge but do all this in a single model. Previous methods achieve this by having separate detection heads on a common backbone but that results in a significant increase in parameters. In this work, we present Mixture-of-Experts as a solution, highlighting that MoEs are much more than a scalability tool. We propose Dataset-Aware Mixture-of-Experts, DAMEX where we train the experts to become an `expert' of a dataset by learning to route each dataset tokens to its mapped expert. Experiments on Universal Object-Detection Benchmark show that we outperform the existing state-of-the-art by average +10.2 AP score and improve over our non-MoE baseline by average +2.0 AP score. We also observe consistent gains while mixing datasets with (1) limited availability, (2) disparate domains and (3) divergent label sets. Further, we qualitatively show that DAMEX is robust against expert representation collapse.
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。
