mlsanityData to 14 Oct 2026

Locally Scale-Invariant Convolutional Neural Networks

arXiv 1412.5104 ↗First posted 16 Dec 2014cs.CV cs.LG cs.NEcited by 34

Not on the map. Why?

Abstract (arXiv)

Convolutional Neural Networks (ConvNets) have shown excellent results on many visual classification tasks. With the exception of ImageNet, these datasets are carefully crafted such that objects are well-aligned at similar scales. Naturally, the feature learning problem gets more challenging as the amount of variation in the data increases, as the models have to learn to be invariant to certain changes in appearance. Recent results on the ImageNet dataset show that given enough data, ConvNets can learn such invariances producing very discriminative features [1]. But could we do more: use less parameters, less data, learn more discriminative features, if certain invariances were built into the learning process? In this paper we present a simple model that allows ConvNets to learn features in a locally scale-invariant manner without increasing the number of model parameters. We show on a modified MNIST dataset that when faced with scale variation, building in scale-invariance allows ConvNets to learn more discriminative features with reduced chances of over-fitting.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Dec 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 10; 2022: 8; 2023: 10; 2024: 2; 2025: 1; 2026: 3.

34 papers.

Sort:

  1. 2024Estimating Body and Hand Motion in an Ego-sensed Worldcited by 58
  2. 2022DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detectioncited by 48
  3. 2022Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentationcited by 37
  4. 2021DISCO: accurate Discrete Scale Convolutionscited by 36
  5. 2021Resolution learning in deep convolutional networks using scale-space theorycited by 26
  6. 2021Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scalescited by 17
  7. 2023Truly Scale-Equivariant Deep Nets with Fourier Layerscited by 16
  8. 2021Group Equivariant Subsamplingcited by 15
  9. 2023Scale-Equivariant UNet for Histopathology Image Segmentationcited by 11
  10. 2023Riesz networks: scale invariant neural networks in a single forward passcited by 8
  11. 2023Canonical Factors for Hybrid Neural Fieldscited by 8
  12. 2021Deformation Robust Roto-Scale-Translation Equivariant CNNscited by 7
22 more
  1. 2022Improving the Sample-Complexity of Deep Classification Networks with Invariant Integrationcited by 7
  2. 2021Sampling Equivariant Self-attention Networks for Object Detection in Aerial Imagescited by 6
  3. 2023Scale-Equivariant Deep Learning for 3D Datacited by 6
  4. 2021Downbeat Tracking with Tempo-Invariant Convolutional Neural Networkscited by 4
  5. 2023Empowering Networks With Scale and Rotation Equivariance Using A Similarity Convolutioncited by 4
  6. 2024Scale generalisation properties of extended scale-covariant and scale-invariant Gaussian derivative networks on image datasets with spatial scaling variationscited by 3
  7. 2022Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimizationcited by 2
  8. 2022Just a Matter of Scale? Reevaluating Scale Equivariance in Convolutional Neural Networkscited by 2
  9. 2023Equivariant and Steerable Neural Networks: A review with special emphasis on the symmetric groupcited by 2
  10. 2023Deep Neural Networks with Efficient Guaranteed Invariancescited by 2
  11. 2023TpopT: Efficient Trainable Template Optimization on Low-Dimensional Manifoldscited by 2
  12. 2025Local Scale Equivariance with Latent Deep Equilibrium Canonicalizercited by 2
  13. 2021Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networkscited by 1
  14. 2023Evaluating Machine Learning Models with NERO: Non-Equivariance Revealed on Orbitscited by 1
  15. 2026Learning and extrapolating scale-invariant processescited by 1
  16. 2021Characterizing and Taming Resolution in Convolutional Neural Networkscited by 0
  17. 2021Wiggling Weights to Improve the Robustness of Classifierscited by 0
  18. 2022Euclidean Invariant Recognition of 2D Shapes Using Histograms of Magnitudes of Local Fourier-Mellin Descriptorscited by 0
  19. 2022Scale dependant layer for self-supervised nuclei encodingcited by 0
  20. 2022A Rotation Meanout Network with Invariance for Dermoscopy Image Classification and Retrievalcited by 0
  21. 2026Scale-invariant Gaussian derivative residual networkscited by 0
  22. 2026Image-Scale Robustness and Visual Recognition Performance: A Cross-Architecture Analysiscited by 0