# ME R-CNN: Multi-Expert R-CNN for Object Detection

arXiv: https://arxiv.org/abs/1704.01069 · HTML: https://mlsanity.com/paper/1704.01069/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2017.

## Built on by (most cited first, 13 of 13)

- [Dense Learning based Semi-Supervised Object Detection](https://mlsanity.com/paper/2204.07300/) (2022)
- [MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection](https://mlsanity.com/paper/2309.14976/) (2023)
- [Circle Representation for Medical Object Detection](https://mlsanity.com/paper/2110.12093/) (2021)
- [Revisiting Single-gated Mixtures of Experts](https://mlsanity.com/paper/2304.05497/) (2023)
- [Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification](https://mlsanity.com/paper/2204.03144/) (2022)
- [Diversifying Human Pose in Synthetic Data for Aerial-view Human Detection](https://mlsanity.com/paper/2405.15939/) (2024)
- [DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors](https://mlsanity.com/paper/2204.02890/) (2022)
- [Diminishing Domain Bias by Leveraging Domain Labels in Object Detection on UAVs](https://mlsanity.com/paper/2101.12677/) (2021)
- [Training Domain-invariant Object Detector Faster with Feature Replay and Slow Learner](https://mlsanity.com/paper/2105.14693/) (2021)
- [NFANet: A Novel Method for Weakly Supervised Water Extraction from High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2201.03686/) (2022)
- [Validation of object detection in UAV-based images using synthetic data](https://mlsanity.com/paper/2201.06629/) (2022)
- [SynPlay: Large-Scale Synthetic Human Data with Real-World Diversity for Aerial-View Perception](https://mlsanity.com/paper/2408.11814/) (2024)
- [HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images](https://mlsanity.com/paper/2604.18866/) (2026)

## Abstract (arXiv)

We introduce Multi-Expert Region-based Convolutional Neural Network (ME R-CNN) which is equipped with multiple experts (ME) where each expert is learned to process a certain type of regions of interest (RoIs). This architecture better captures the appearance variations of the RoIs caused by different shapes, poses, and viewing angles. In order to direct each RoI to the appropriate expert, we devise a novel "learnable" network, which we call, expert assignment network (EAN). EAN automatically learns the optimal RoI-expert relationship even without any supervision of expert assignment. As the major components of ME R-CNN, ME and EAN, are mutually affecting each other while tied to a shared network, neither an alternating nor a naive end-to-end optimization is likely to fail. To address this problem, we introduce a practical training strategy which is tailored to optimize ME, EAN, and the shared network in an end-to-end fashion. We show that both of the architectures provide considerable performance increase over the baselines on PASCAL VOC 07, 12, and MS COCO datasets.