mlsanityData to 14 Oct 2026

Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks

arXiv 2210.08001 ↗First posted 14 Oct 2022cs.CV cs.AI cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

We propose learnable polyphase sampling (LPS), a pair of learnable down/upsampling layers that enable truly shift-invariant and equivariant convolutional networks. LPS can be trained end-to-end from data and generalizes existing handcrafted downsampling layers. It is widely applicable as it can be integrated into any convolutional network by replacing down/upsampling layers. We evaluate LPS on image classification and semantic segmentation. Experiments show that LPS is on-par with or outperforms existing methods in both performance and shift consistency. For the first time, we achieve true shift-equivariance on semantic segmentation (PASCAL VOC), i.e., 100% shift consistency, outperforming baselines by an absolute 3.3%.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 41 of its 74 references that are in the map. First posted on arXiv 14 Oct 2022.

Builds on

41 of 74 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  8. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  9. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  10. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  11. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  12. 2017Deep Setscited by 1,421
29 more
  1. 2016Group Equivariant Convolutional Networkscited by 1,165
  2. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  3. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  4. 2013Network In Networkcited by 605
  5. 2018Spherical CNNscited by 456
  6. 2019General E(2)-Equivariant Steerable CNNscited by 446
  7. 2019Making Convolutional Networks Shift-Invariant Againcited by 391
  8. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 354
  9. 2018Invariant and Equivariant Graph Networkscited by 346
  10. 2019Gauge Equivariant Convolutional Networks and the Icosahedral CNNcited by 267
  11. 2018Why do deep convolutional networks generalize so poorly to small image transformations?cited by 198
  12. 2018Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Networkcited by 171
  13. 2017Equivariance Through Parameter-Sharingcited by 141
  14. 2020On Learning Sets of Symmetric Elementscited by 98
  15. 2020Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphscited by 92
  16. 2018Deep Models of Interactions Across Setscited by 69
  17. 2020Attentive Group Equivariant Convolutional Networkscited by 63
  18. 2020Delving Deeper into Anti-aliasing in ConvNetscited by 60
  19. 2020Truly shift-invariant convolutional neural networkscited by 53
  20. 2013Stochastic Pooling for Regularization of Deep Convolutional Neural Networkscited by 48
  21. 2019PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learningcited by 47
  22. 2022SpeqNets: Sparsity-aware Permutation-equivariant Graph Networkscited by 37
  23. 2015Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Treecited by 36
  24. 2019Chirality Nets for Human Pose Regressioncited by 31
  25. 2021Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learningcited by 18
  26. 2022Equivariance Discovery by Learned Parameter-Sharingcited by 18
  27. 2021Equivariant Networks for Pixelized Spherescited by 16
  28. 2021Truly shift-equivariant convolutional neural networks with adaptive polyphase upsamplingcited by 10
  29. 2019Building Deep, Equivariant Capsule Networkscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 4; 2025: 9; 2026: 1.

18 papers.

Sort:

  1. 2023Making Vision Transformers Truly Shift-Equivariantcited by 16
  2. 2023Truly Scale-Equivariant Deep Nets with Fourier Layerscited by 16
  3. 2023Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activationscited by 11
  4. 2023Investigating Shift Equivalence of Convolutional Neural Networks in Industrial Defect Segmentationcited by 6
  5. 2024Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase Samplingcited by 6
  6. 2025Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learningcited by 5
  7. 2025Enhancing Image Restoration Transformer via Adaptive Translation Equivariancecited by 5
  8. 2025Group Downsampling with Equivariant Anti-aliasingcited by 3
  9. 2025Local Scale Equivariance with Latent Deep Equilibrium Canonicalizercited by 2
  10. 2025CLIPSym: Delving into Symmetry Detection with CLIPcited by 2
  11. 2025Alias-Free ViT: Fractional Shift Invariance via Linear Attentioncited by 2
  12. 2024Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Timecited by 1
6 more
  1. 2025Translation-Equivariance of Normalization Layers and Aliasing in Convolutional Neural Networkscited by 1
  2. 2024Lost in Translation: Modern Neural Networks Still Struggle With Small Realistic Image Transformationscited by 0
  3. 2024Adaptive Sampling for Continuous Group Equivariant Neural Networkscited by 0
  4. 2025Towards Foundation Models for Cryo-ET Subtomogram Analysiscited by 0
  5. 2025Shift-Equivariant Complex-Valued Convolutional Neural Networkscited by 0
  6. 2026Tunable Soft Equivariance with Guaranteescited by 0