mlsanityData to 7 Oct 2026

Semantic Segmentation using Neural Ordinary Differential Equations

arXiv 2209.08667 ↗First posted 18 Sep 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

The idea of neural Ordinary Differential Equations (ODE) is to approximate the derivative of a function (data model) instead of the function itself. In residual networks, instead of having a discrete sequence of hidden layers, the derivative of the continuous dynamics of hidden state can be parameterized by an ODE. It has been shown that this type of neural network is able to produce the same results as an equivalent residual network for image classification. In this paper, we design a novel neural ODE for the semantic segmentation task. We start by a baseline network that consists of residual modules, then we use the modules to build our neural ODE network. We show that our neural ODE is able to achieve the state-of-the-art results using 57% less memory for training, 42% less memory for testing, and 68% less number of parameters. We evaluate our model on the Cityscapes, CamVid, LIP, and PASCAL-Context datasets.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 18 Sep 2022.

Builds on

35 of 47 references.

References · 35

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  8. 2018Neural Ordinary Differential Equationscited by 3,733
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  10. 2016Pyramid Scene Parsing Networkcited by 2,472
  11. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  12. 2016Identity Mappings in Deep Residual Networkscited by 1,960
23 more
  1. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  2. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  3. 2017Mixed Precision Trainingcited by 1,135
  4. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  5. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  6. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  7. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  8. 2016FractalNet: Ultra-Deep Neural Networks without Residualscited by 216
  9. 2017The Reversible Residual Network: Backpropagation Without Storing Activationscited by 215
  10. 2017Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equationscited by 203
  11. 2017Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsingcited by 109
  12. 2017In-Place Activated BatchNorm for Memory-Optimized Training of DNNscited by 81
  13. 2018Devil in the Details: Towards Accurate Single and Multiple Human Parsingcited by 64
  14. 2017Image-based Localization using Hourglass Networkscited by 63
  15. 2017Residual Conv-Deconv Grid Network for Semantic Segmentationcited by 57
  16. 2016PolyNet: A Pursuit of Structural Diversity in Very Deep Networkscited by 38
  17. 2016Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFscited by 27
  18. 2018Convolutional Neural Networks combined with Runge-Kutta Methodscited by 18
  19. 2018Interlinked Convolutional Neural Networks for Face Parsingcited by 16
  20. 2019Neural Ordinary Differential Equations for Semantic Segmentation of Individual Colon Glandscited by 15
  21. 2018Convolutional Neural Networks with Alternately Updated Cliquecited by 14
  22. 2019Neural ODEs for Image Segmentation with Level Setscited by 4
  23. 2014Training deep neural networks with low precision multiplicationscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 3.

6 papers.

  1. 2023Sentence Attention Blocks for Answer Groundingcited by 8
  2. 2023Empowering Visually Impaired Individuals: A Novel Use of Apple Live Photos and Android Motion Photoscited by 6
  3. 2023Improving Normalization with the James-Stein Estimatorcited by 6
  4. 2024On the Effect of Image Resolution on Semantic Segmentationcited by 1
  5. 2024Multi-Scale Semantic Segmentation with Modified MBConv Blockscited by 0
  6. 2024Early Fusion of Features for Semantic Segmentationcited by 0