mlsanityData to 7 Oct 2026

Diversified Dynamic Routing for Vision Tasks

arXiv 2209.13071 ↗First posted 26 Sep 2022cs.CVcited by 0

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

Abstract (arXiv)

Deep learning models for vision tasks are trained on large datasets under the assumption that there exists a universal representation that can be used to make predictions for all samples. Whereas high complexity models are proven to be capable of learning such representations, a mixture of experts trained on specific subsets of the data can infer the labels more efficiently. However using mixture of experts poses two new problems, namely (i) assigning the correct expert at inference time when a new unseen sample is presented. (ii) Finding the optimal partitioning of the training data, such that the experts rely the least on common features. In Dynamic Routing (DR) a novel architecture is proposed where each layer is composed of a set of experts, however without addressing the two challenges we demonstrate that the model reverts to using the same subset of experts. In our method, Diversified Dynamic Routing (DivDR) the model is explicitly trained to solve the challenge of finding relevant partitioning of the data and assigning the correct experts in an unsupervised approach. We conduct several experiments on semantic segmentation on Cityscapes and object detection and instance segmentation on MS-COCO showing improved performance over several baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 42 of its 53 references that are in the map. First posted on arXiv 26 Sep 2022.

Builds on

42 of 53 references.

References · 42

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2017Mask R-CNNcited by 7,259
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  11. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  12. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
30 more
  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  2. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  3. 2015Fast R-CNNcited by 2,930
  4. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  6. 2016Pyramid Scene Parsing Networkcited by 2,472
  7. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  9. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  10. 2020Knowledge Distillation: A Surveycited by 1,578
  11. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  12. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  13. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  14. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  15. 2019Objects as Pointscited by 1,172
  16. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  17. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  18. 2019Panoptic Feature Pyramid Networkscited by 644
  19. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
  20. 2017BlockDrop: Dynamic Inference Paths in Residual Networkscited by 185
  21. 2017Convolutional Networks with Adaptive Inference Graphscited by 147
  22. 2019Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networkscited by 118
  23. 2018Searching for Efficient Multi-Scale Architectures for Dense Image Predictioncited by 96
  24. 2020Learning Dynamic Routing for Semantic Segmentationcited by 79
  25. 2015Metric Learning with Adaptive Density Discriminationcited by 40
  26. 2018Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cellscited by 39
  27. 2019Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Searchcited by 39
  28. 2021HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformerscited by 39
  29. 2019SqueezeNAS: Fast neural architecture search for faster semantic segmentationcited by 31
  30. 2019Learnable Tree Filter for Structure-preserving Feature Transformcited by 25

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Routers in Vision Mixture of Experts: An Empirical Study
  2. 2025Guiding the Experts: Semantic Priors for Efficient and Focused MoE Routing
  3. 2025Input Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of Experts
  4. 2026HI-MoE: Hierarchical Instance-Conditioned Mixture-of-Experts for Object Detection
  5. 2025Long-Tailed Distribution-Aware Router For Mixture-of-Experts in Large Vision-Language Model
  6. 2026Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation
  7. 2018Deep Mixture of Experts via Shallow Embedding
  8. 2026Teacher-Guided Routing for Sparse Vision Mixture-of-Experts