mlsanityData to 7 Oct 2026

Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations

arXiv 2008.09662 ↗First posted 21 Aug 2020cs.LG eess.IVcited by 20

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

Abstract (arXiv)

We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate results can vary for different input space partitions. Therefore, we consider mixtures where experts require different amounts of data, and train a sparse gating function to divide the input space for each expert. By appropriate hyperparameter selection, our approach is able to bias mixtures of experts towards selecting specific experts over others. In this way, we show that the data transfer optimization between visual sensing and processing can be solved as a convex optimization problem.To demonstrate the relation between data availability and performance, we evaluate biased mixtures on a range of mainstream computer vision problems, namely: (i) single shot detection, (ii) image super resolution, and (iii) realtime video action classification. For all cases, and when experts constitute modified baselines to meet different limits on allowed data utility, biased mixtures significantly outperform previous work optimized to meet the same constraints on available data.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts. Builds on 34 of its 57 references that are in the map. First posted on arXiv 21 Aug 2020.

Builds on

34 of 57 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  7. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  8. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  10. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  11. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  12. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
22 more
  1. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  2. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  3. 2016Pixel Recurrent Neural Networkscited by 814
  4. 2016End-to-end Optimized Image Compressioncited by 673
  5. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  6. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  7. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
  8. 2016Convolutional Two-Stream Network Fusion for Video Action Recognitioncited by 384
  9. 2015Adversarial Autoencoderscited by 359
  10. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  11. 2016Speed/accuracy trade-offs for modern convolutional object detectorscited by 198
  12. 2017Generate To Adapt: Aligning Domains using Generative Adversarial Networkscited by 183
  13. 2015Conditional Computation in Neural Networks for faster modelscited by 166
  14. 2016Discrete Variational Autoencoderscited by 124
  15. 2017Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networkscited by 107
  16. 2018Practical Full Resolution Learned Lossless Image Compressioncited by 93
  17. 2014Rigid-Motion Scattering for Texture Classificationcited by 52
  18. 2017Video Salient Object Detection via Fully Convolutional Networkscited by 46
  19. 2017On the Integration of Optical Flow and Action Recognitioncited by 42
  20. 2017Video Classification With CNNs: Using The Codec As A Spatio-Temporal Activity Sensorcited by 3
  21. 2018Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videoscited by 2
  22. 2018Rate-Accuracy Trade-Off In Video Classification With Deep Convolutional Neural Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 4; 2024: 5; 2025: 5; 2026: 1.

20 papers.

Sort:

By area:

  1. 2021Scaling Vision with Sparse Mixture of Expertscited by 740
  2. 2022M3ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-designcited by 97
  3. 2024Mixtures of Experts Unlock Parameter Scaling for Deep RLcited by 75
  4. 2023Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformerscited by 59
  5. 2022Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEscited by 58
  6. 2022Residual Mixture of Expertscited by 39
  7. 2023PDPP: Projected Diffusion for Procedure Planning in Instructional Videoscited by 36
  8. 2023Robust Mixture-of-Expert Training for Convolutional Neural Networkscited by 30
  9. 2023Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Expertscited by 27
  10. 2024Routers in Vision Mixture of Experts: An Empirical Studycited by 22
  11. 2024Mixture of Experts in a Mixture of RL settingscited by 21
  12. 2022Spatial Mixture-of-Expertscited by 14
8 more
  1. 2024Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RLcited by 14
  2. 2024Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularizationcited by 11
  3. 2025HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReIDcited by 10
  4. 2025Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Designcited by 6
  5. 2025A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusioncited by 5
  6. 2026On the Holistic Approach for Detecting Human Image Forgerycited by 5
  7. 2025Token-Level Prompt Mixture with Parameter-Free Routing for Federated Domain Generalizationcited by 0
  8. 2025SHMoAReg: Spark Deformable Image Registration via Spatial Heterogeneous Mixture of Experts and Attention Headscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Mixture-of-Experts Models in Vision: Routing, Optimization, and Generalization
  2. 2024Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
  3. 2023DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets
  4. 2025Mixture of Many Zero-Compute Experts: A High-Rate Quantization Theory Perspective
  5. 2026VidPrism: Heterogeneous Mixture of Experts for Image-to-Video Transfer
  6. 2023MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection
  7. 2024Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
  8. 2025Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks