mlsanityData to 7 Oct 2026

Maxout Networks

arXiv 1302.4389 ↗First posted 18 Feb 2013stat.ML cs.LGcited by 186

Not on the map. Why?

Abstract (arXiv)

We consider the problem of designing models to leverage a recently introduced approximate model averaging technique called dropout. We define a simple new model called maxout (so named because its output is the max of a set of inputs, and because it is a natural companion to dropout) designed to both facilitate optimization by dropout and improve the accuracy of dropout's fast approximate model averaging technique. We empirically verify that the model successfully accomplishes both of these tasks. We use maxout and dropout to demonstrate state of the art classification performance on four benchmark datasets: MNIST, CIFAR-10, CIFAR-100, and SVHN.

Key facts. Cited by 186 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Feb 2013.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 55; 2022: 44; 2023: 32; 2024: 18; 2025: 20; 2026: 17.

186 papers.

Sort:

By area:

  1. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  2. 2021Activation Functions in Deep Learning: A Comprehensive Survey and Benchmarkcited by 153
  3. 2021MoEfication: Transformer Feed-forward Layers are Mixtures of Expertscited by 149
  4. 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learningcited by 143
  5. 2021Recent Advances in Reinforcement Learning in Financecited by 102
  6. 2022B-cos Networks: Alignment is All We Need for Interpretabilitycited by 88
  7. 2023Collaborative Perception in Autonomous Driving: Methods, Datasets and Challengescited by 87
  8. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  9. 2023Boosting Multi-modal Model Performance with Adaptive Gradient Modulationcited by 71
  10. 2021Model Complexity of Deep Learning: A Surveycited by 64
  11. 2023SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficientcited by 58
  12. 2022HYDRA: Competing convolutional kernels for fast and accurate time series classificationcited by 53
38 more
  1. 2023Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based acceleratorscited by 42
  2. 2021Reflash Dropout in Image Super-Resolutioncited by 41
  3. 2023When Deep Learning Meets Polyhedral Theory: A Surveycited by 39
  4. 2022AdaBin: Improving Binary Neural Networks with Adaptive Binary Setscited by 38
  5. 2021Sharp bounds for the number of regions of maxout networks and vertices of Minkowski sumscited by 37
  6. 2021Neuro-Symbolic Inductive Logic Programming with Logical Neural Networkscited by 36
  7. 2023B-cos Alignment for Inherently Interpretable CNNs and Vision Transformerscited by 31
  8. 2022How important are activation functions in regression and classification? A survey, performance comparison, and future directionscited by 29
  9. 2022Attention Diversification for Domain Generalizationcited by 29
  10. 2021What can linear interpolation of neural network loss landscapes tell us?cited by 27
  11. 2022Improved Bounds on Neural Complexity for Representing Piecewise Linear Functionscited by 26
  12. 2022PillarGrid: Deep Learning-based Cooperative Perception for 3D Object Detection from Onboard-Roadside LiDARcited by 25
  13. 2023MaxK-GNN: Extremely Fast GPU Kernel Design for Accelerating Graph Neural Networks Trainingcited by 25
  14. 2021Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classificationcited by 23
  15. 2024CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competitioncited by 23
  16. 2022On the Number of Regions of Piecewise Linear Neural Networkscited by 21
  17. 2022A Survey and Framework of Cooperative Perception: From Heterogeneous Singleton to Hierarchical Cooperationcited by 21
  18. 2025Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learningcited by 19
  19. 2021FastSurferVINN: Building Resolution-Independence into Deep Learning Segmentation Methods -- A Solution for HighRes Brain MRIcited by 18
  20. 2022Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithmcited by 17
  21. 2021On the Expected Complexity of Maxout Networkscited by 15
  22. 2023Learning Specialized Activation Functions for Physics-informed Neural Networkscited by 14
  23. 2024DropKAN: Regularizing KANs by masking post-activationscited by 14
  24. 2021Neural Network Quantization for Efficient Inference: A Surveycited by 13
  25. 2025Mamba Modulation: On the Length Generalization of Mambacited by 13
  26. 2021Activation Functions in Artificial Neural Networks: A Systematic Overviewcited by 12
  27. 2022Graph-adaptive Rectified Linear Unit for Graph Neural Networkscited by 12
  28. 2022SwinCheX: Multi-label classification on chest X-ray images with transformerscited by 12
  29. 2024B-cosification: Transforming Deep Neural Networks to be Inherently Interpretablecited by 12
  30. 2021Connections between Numerical Algorithms for PDEs and Neural Networkscited by 10
  31. 2023Elephant Neural Networks: Born to Be a Continual Learnercited by 10
  32. 2021Sample Complexity and Overparameterization Bounds for Temporal Difference Learning with Neural Network Approximationcited by 9
  33. 2021edge-SR: Super-Resolution For The Massescited by 9
  34. 2022Lower and Upper Bounds for Numbers of Linear Regions of Graph Convolutional Networkscited by 9
  35. 2022SecureFedYJ: a safe feature Gaussianization protocol for Federated Learningcited by 9
  36. 2021Min-Max-Plus Neural Networkscited by 8
  37. 2022Learning Energy Networks with Generalized Fenchel-Young Lossescited by 8
  38. 2023Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regionscited by 8

50 most cited of 186 All 186 (JSON)