mlsanityData to 14 Oct 2026

Offset equivariant networks and their applications

arXiv 2207.00292 ↗First posted 1 Jul 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

In this paper we present a framework for the design and implementation of offset equivariant networks, that is, neural networks that preserve in their output uniform increments in the input. In a suitable color space this kind of networks achieves equivariance with respect to the photometric transformations that characterize changes in the lighting conditions. We verified the framework on three different problems: image recognition, illuminant estimation, and image inpainting. Our experiments show that the performance of offset equivariant networks are comparable to those in the state of the art on regular data. Differently from conventional networks, however, equivariant networks do behave consistently well when the color of the illuminant changes.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 20 of its 50 references that are in the map. First posted on arXiv 1 Jul 2022.

Builds on

20 of 50 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  6. 2016Group Equivariant Convolutional Networkscited by 1,165
  7. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 370
  8. 2018Invariant and Equivariant Graph Networkscited by 346
  9. 2016Steerable CNNscited by 305
  10. 2018On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groupscited by 300
  11. 2013Maxout Networkscited by 187
  12. 2017Equivariance Through Parameter-Sharingcited by 141
8 more
  1. 2018Universal approximations of invariant maps by neural networkscited by 127
  2. 2017Deep Image Harmonizationcited by 120
  3. 2020Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphscited by 92
  4. 2020Deep Multi-View Enhancement Hashing for Image Retrievalcited by 27
  5. 2015Color Constancy Using CNNscited by 21
  6. 2020Depth image denoising using nuclear norm and learning graph modelcited by 20
  7. 2016Approaching the Computational Color Constancy as a Classification Problem through Deep Learningcited by 12
  8. 2019Color Cerberuscited by 1

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 0; 2025: 3.

6 papers.

  1. 2023Color Equivariant Convolutional Networkscited by 7
  2. 2023Loss it right: Euclidean and Riemannian Metrics in Learning-based Visual Odometrycited by 6
  3. 2025Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelinescited by 4
  4. 2023DUET: 2D Structured and Approximately Equivariant Representationscited by 2
  5. 2025Normalize Filters! Classical Wisdom for Deep Visioncited by 1
  6. 2025Log NeRF: Comparing Spaces for Learning Radiance Fieldscited by 0