# Multi-Domain Learning with Global Expert Mapping

arXiv: https://arxiv.org/abs/2604.18842 · HTML: https://mlsanity.com/paper/2604.18842/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 49 of its 65 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 30 of 49)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [BASE Layers: Simplifying Training of Large, Sparse Models](https://mlsanity.com/paper/2103.16716/) (2021)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [Unified Scaling Laws for Routed Language Models](https://mlsanity.com/paper/2202.01169/) (2022)
- [From Sparse to Soft Mixtures of Experts](https://mlsanity.com/paper/2308.00951/) (2023)
- [Cross-Domain Weakly-Supervised Object Detection through Progressive Domain Adaptation](https://mlsanity.com/paper/1803.11365/) (2018)
- [Omnivore: A Single Model for Many Visual Modalities](https://mlsanity.com/paper/2201.08377/) (2022)
- [Scaling Laws for Fine-Grained Mixture of Experts](https://mlsanity.com/paper/2402.07871/) (2024)
- [Efficient parametrization of multi-domain deep neural networks](https://mlsanity.com/paper/1803.10082/) (2018)
- [On the Representation Collapse of Sparse Mixture of Experts](https://mlsanity.com/paper/2204.09179/) (2022)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts](https://mlsanity.com/paper/2405.11273/) (2024)
- [Towards Universal Object Detection by Domain Attention](https://mlsanity.com/paper/1904.04402/) (2019)
- [Sparse Mixture-of-Experts are Domain Generalizable Learners](https://mlsanity.com/paper/2206.04046/) (2022)
- [Harder Tasks Need More Experts: Dynamic Routing in MoE Models](https://mlsanity.com/paper/2403.07652/) (2024)
- [MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts](https://mlsanity.com/paper/2410.07348/) (2024)
- [ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing](https://mlsanity.com/paper/2412.14711/) (2024)
- [Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-scale Lesion Database](https://mlsanity.com/paper/1711.10535/) (2017)
- [Sparsity-Constrained Optimal Transport](https://mlsanity.com/paper/2209.15466/) (2022)

## Abstract (arXiv)

Human perception generalizes well across different domains, but most vision models struggle beyond their training data. This gap motivates multi-dataset learning, where a single model is trained on diverse datasets to improve robustness under domain shifts. However, unified training remains challenging due to inconsistencies in data distributions and label semantics. Mixture-of-Experts (MoE) models provide a scalable solution by routing inputs to specialized subnetworks (experts). Yet, existing MoEs often fail to specialize effectively, as their load-balancing mechanisms enforce uniform input distribution across experts. This fairness conflicts with domain-aware routing, causing experts to learn redundant representations, and reducing performance especially on rare or out-of-distribution domains. We propose GEM (Global Expert Mapping), a planner-compiler framework that replaces the learned router with a global scheduler. Our planner, based on linear programming relaxation, computes a fractional assignment of datasets to experts, while the compiler applies hierarchical rounding to convert this soft plan into a deterministic, capacity-aware mapping. Unlike prior MoEs, GEM avoids balancing loss, resolves the conflict between fairness and specialization, and produces interpretable routing. Experiments show that GEM-DINO achieves state-of-the-art performance on the UODB benchmark, with notable gains on underrepresented datasets and solves task interference in few-shot adaptation scenarios.