mlsanityData to 7 Oct 2026

Neural TMDlayer: Modeling Instantaneous flow of features via SDE Generators

arXiv 2108.08891 ↗First posted 19 Aug 2021cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We study how stochastic differential equation (SDE) based ideas can inspire new modifications to existing algorithms for a set of problems in computer vision. Loosely speaking, our formulation is related to both explicit and implicit strategies for data augmentation and group equivariance, but is derived from new results in the SDE literature on estimating infinitesimal generators of a class of stochastic processes. If and when there is nominal agreement between the needs of an application/task and the inherent properties and behavior of the types of processes that we can efficiently handle, we obtain a very simple and efficient plug-in layer that can be incorporated within any existing network architecture, with minimal modification and only a few additional parameters. We show promising experiments on a number of vision tasks including few shot learning, point cloud transformers and deep variational segmentation obtaining efficiency or performance improvements.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 64 references that are in the map. First posted on arXiv 19 Aug 2021.

Builds on

40 of 64 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2018Neural Ordinary Differential Equationscited by 3,733
  6. 2020Longformer: The Long-Document Transformercited by 3,362
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  10. 2016Matching Networks for One Shot Learningcited by 2,246
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  12. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
28 more
  1. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  2. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  3. 2020PCT: Point cloud transformercited by 730
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  5. 2015Train faster, generalize better: Stability of stochastic gradient descentcited by 547
  6. 2021Nystr"omformer: A Nystr"om-Based Algorithm for Approximating Self-Attentioncited by 468
  7. 2018Spherical CNNscited by 452
  8. 2019Augmented Neural ODEscited by 396
  9. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  10. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  11. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 244
  12. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  13. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  14. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  15. 2019Variational Physics-Informed Neural Networks For Solving Partial Differential Equationscited by 144
  16. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  17. 2014Hypercolumns for Object Segmentation and Fine-grained Localizationcited by 128
  18. 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
  19. 2017Stochastic gradient descent performs variational inference, converges to limit cycles for deep networkscited by 108
  20. 2019Neural SDE: Stabilizing Neural ODE Networks with Stochastic Noisecited by 98
  21. 2019Fast Interactive Object Annotation with Curve-GCNcited by 95
  22. 2019A-CNN: Annularly Convolutional Neural Networks on Point Cloudscited by 66
  23. 2018Learning deep structured active contours end-to-endcited by 38
  24. 2019Learning Generalized Transformation Equivariant Representations via Autoencoding Transformationscited by 22
  25. 2019Learning an Effective Equivariant 3D Descriptor Without Supervisioncited by 14
  26. 2020Deep Variational Instance Segmentationcited by 7
  27. 2019End-to-End Deep Convolutional Active Contours for Image Segmentationcited by 5
  28. 2021Simpler Certified Radius Maximization by Propagating Covariancescited by 2

Built on by

Not cited yet.