mlsanityData to 14 Oct 2026

Domain-Specialized Object Detection via Model-Level Mixtures of Experts

arXiv 2604.18256 ↗First posted 20 Apr 2026cs.CV cs.LGcited by 0

On the map: Mixture-of-experts → Vision mixture-of-experts

Abstract (arXiv)

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/.

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 20 of its 37 references that are in the map. First posted on arXiv 20 Apr 2026.

Builds on

20 of 37 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers5 Sep
  2. 2023MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection26 Sep
  3. 2022Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability22 Apr
  4. 2021Scaling Vision with Sparse Mixture of Experts10 Jun

Other references · 16

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  3. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  4. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  5. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,631
  6. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  7. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  8. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  9. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  10. 2024DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Modelscited by 867
  11. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 425
  12. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 382
4 more
  1. 2017MegDet: A Large Mini-Batch Object Detectorcited by 66
  2. 2016Network of Experts for Large-Scale Image Categorizationcited by 54
  3. 2017Choosing Smartly: Adaptive Multimodal Fusion for Object Detection in Changing Environmentscited by 34
  4. 2015Deep CNN Ensemble with Data Augmentation for Object Detectioncited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026HI-MoE: Hierarchical Instance-Conditioned Mixture-of-Experts for Object Detection
  2. 2024Mixture of Experts in Image Classification: What's the Sweet Spot?
  3. 2024Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
  4. 2026Mixture-of-Experts Models in Vision: Routing, Optimization, and Generalization
  5. 2025Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-time Open-Vocabulary Object Detection
  6. 2026Mixture of Experts with Soft Nearest Neighbor Loss: Resolving Expert Collapse via Representation Disentanglement
  7. 2023DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets
  8. 2025Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks