mlsanityData to 14 Oct 2026

Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer

arXiv 2508.14187 ↗First posted 19 Aug 2025cs.CV cs.GR cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Scale variation is a fundamental challenge in computer vision. Objects of the same class can have different sizes, and their perceived size is further affected by the distance from the camera. These variations are local to the objects, i.e., different object sizes may change differently within the same image. To effectively handle scale variations, we present a deep equilibrium canonicalizer (DEC) to improve the local scale equivariance of a model. DEC can be easily incorporated into existing network architectures and can be adapted to a pre-trained model. Notably, we show that on the competitive ImageNet benchmark, DEC improves both model performance and local scale consistency across four popular pre-trained deep-nets, e.g., ViT, DeiT, Swin, and BEiT. Our code is available at https://github.com/ashiq24/local-scale-equivariance.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 55 of its 74 references that are in the map. First posted on arXiv 19 Aug 2025.

Builds on

55 of 74 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2023Segment Anythingcited by 8,234
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  8. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  9. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  10. 2016Pyramid Scene Parsing Networkcited by 2,479
  11. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  12. 2021Vision Transformers for Dense Predictioncited by 1,803
38 more
  1. 2017Deformable Convolutional Networkscited by 1,488
  2. 2015Spatial Transformer Networkscited by 1,429
  3. 2017Deep Setscited by 1,421
  4. 2016Group Equivariant Convolutional Networkscited by 1,165
  5. 2021Multiscale Vision Transformerscited by 897
  6. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  7. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 720
  8. 2019Deep Equilibrium Modelscited by 615
  9. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  10. 2019Making Convolutional Networks Shift-Invariant Againcited by 391
  11. 2017Learning Steerable Filters for Rotation Equivariant CNNscited by 194
  12. 2021Frame Averaging for Invariant and Equivariant Network Designcited by 168
  13. 2020Multiscale Deep Equilibrium Modelscited by 151
  14. 2019Deep Scale-spaces: Equivariance Over Scalecited by 114
  15. 2019Scale-Equivariant Steerable Networkscited by 110
  16. 2022Equivariance with Learned Canonicalization Functionscited by 109
  17. 2021Multi-Scale High-Resolution Vision Transformer for Semantic Segmentationcited by 92
  18. 2022Tutorial on amortized optimizationcited by 83
  19. 2018Deep Models of Interactions Across Setscited by 69
  20. 2022Deep Equilibrium Optical Flow Estimationcited by 64
  21. 2018Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networkscited by 56
  22. 2019PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learningcited by 47
  23. 2023Equivariant Adaptation of Large Pretrained Modelscited by 41
  24. 2014Scale-Invariant Convolutional Neural Networkscited by 40
  25. 2021DISCO: accurate Discrete Scale Convolutionscited by 36
  26. 2014Locally Scale-Invariant Convolutional Neural Networkscited by 34
  27. 2022ResFormer: Scaling ViTs with Multi-Resolution Trainingcited by 34
  28. 2021FOVEA: Foveated Image Magnification for Autonomous Navigationcited by 32
  29. 2019Chirality Nets for Human Pose Regressioncited by 31
  30. 2023Recurrence without Recurrence: Stable Video Landmark Detection with Deep Equilibrium Modelscited by 27
  31. 2024A Canonicalization Perspective on Invariant and Equivariant Learningcited by 27
  32. 2022Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Modelscited by 22
  33. 2021Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learningcited by 18
  34. 2022Equivariance Discovery by Learned Parameter-Sharingcited by 18
  35. 2022Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networkscited by 18
  36. 2023Making Vision Transformers Truly Shift-Equivariantcited by 16
  37. 2023Truly Scale-Equivariant Deep Nets with Fourier Layerscited by 16
  38. 2021Group Equivariant Subsamplingcited by 15

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Scale-invariant Gaussian derivative residual networkscited by 0
  2. 2026Tunable Soft Equivariance with Guaranteescited by 0