The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Harmonic Networks: Deep Translation and Rotation Equivariance
Abstract
Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map translations. This is not the case for rotations. Global rotation equivariance is typically sought through data augmentation, but patch-wise equivariance is more difficult. We present Harmonic Networks or H-Nets, a CNN exhibiting equivariance to patch-wise translation and 360-rotation. We achieve this by replacing regular CNN filters with circular harmonics, returning a maximal response and orientation for every receptive field patch. H-Nets use a rich, parameter-efficient and fixed computational complexity representation, and we show that deep feature maps within the network encode complicated rotational invariants. We demonstrate that our layers are general enough to be used in conjunction with the latest architectures and techniques, such as deep supervision and batch normalization. We also achieve state-of-the-art classification on rotated-MNIST, and competitive results on other benchmark challenges.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Hinton, G. E., Krizhevsky, A., & Wang, S. D. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-21735-7_6 · Cited by 1,360
Understanding image representations by measuring their equivariance and equivalence
Lenc, K., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298701 · Cited by 366
A mathematical motivation for complex-valued convolutional networks
Tygert, M., Bruna, J., Chintala, S., LeCun, Y., Piantino, S., & Szlam, A. (2016) · Neural Computation · doi:10.1162/neco_a_00824 · Cited by 88 · cited 1×
“, [32]), which use complex filters, but our treatment differs in that the complex phase of the response is explicitly tied to rotation angle.”
Background
Research works printed but not linked: 28
- 10.1109/ICCV.2015.164 · DOI · Paper page
- sohn, 2012, Learning invariant representations with local transformations, Proceedings of the 29th International Conference on Machine Learning 2012
- 10.1109/ICCV.2009.5459468 · DOI
- zeiler, 2014, Visualizing and understanding convolutional networks, Computer Vision — ECCV 2014 — 13th European Conference Zurich Switzerland September 6–12 2014 Proceedings, 818
- hwang, 2015, Pixel-wise deep learning for contour detection, abs 1504 1989
- jacobsen, 2016, Structured receptive fields in cnns, abs 1605 2971
- kivinen, 2014, Visual boundary prediction: A deep neural prediction network and quality dissection, Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics AISTATS 2014, 512
- kokkinos, 2015, Pushing the boundaries of boundary detection using deep learning
- laptev, 2016, TI-POOLING transformation-invariant pooling for feature learning in convolutional neural networks, abs 1604 6318
- 10.1145/1273496.1273556 · DOI · Paper page
- lecun, 1989, Handwritten digit recognition with a back-propagation network, Advances in Neural Information Processing Systems 2 [NIPS Conference, 396
- 10.1109/CVPR.2015.7299024 · DOI · Paper page
- cohen, 2016, Steerable cnns, abs 1612 8498
- 10.1109/CVPR.2012.6247909 · DOI
- cohen, 2016, Group equivariant convolutional networks
- 10.1109/ICPR.2006.1020 · DOI
- simonyan, 2014, Very Deep Convolutional Networks for Large-scale Image Recognition, abs 1409 1556
- dieleman, 2016, Exploiting cyclic symmetry in convolutional neural networks
- ganin, 2014, N4-fields Neural network nearest neighbor fields for image transforms, abs 1406 6558
- 10.1109/34.93808 · DOI · Paper page
- 10.1109/CVPR.2015.7299067 · DOI · Paper page
- 10.1109/TPAMI.2010.161 · DOI · Paper page
- lee, 2015, Deeply-supervised nets, Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics AISTATS 2015
- lenc, 2016, Learning covariant feature detectors, abs 1605 1224
- 10.1109/ICPR.2016.7899932 · DOI
- liu, 2012, 2d/3d rotation-invariant detection using equivariant filters and kernel weighted mapping, 2012 IEEE Conference on Computer Vision and Pattern Recognition, 917
- 10.1109/CVPR.2015.7298904 · DOI
- 10.1162/neco.2010.01-09-953 · DOI
Cited by
Deformable Convolutional Networks
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.89 · Cited by 7,513
Deep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2018) · arXiv · doi:10.48550/arxiv.1809.02165 · Cited by 2,965
Deep Learning for Generic Object Detection: A Survey
Liu, L., Ouyang, W., Wang, X., Fieguth, P., Chen, J., Liu, X., & Pietikäinen, M. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01247-4 · Cited by 2,965
Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
Thomas, N., Smidt, T., Kearnes, S., Yang, L., Li, L., Kohlhoff, K., & Riley, P. (2018) · arXiv · doi:10.48550/arxiv.1802.08219 · Cited by 1,303
ReDet: A Rotation-equivariant Detector for Aerial Object Detection
Han, J., Ding, J., Xue, N., & Xia, G.-S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00281 · Cited by 939
Metadata
- Authors
- Worrall, D. E., Garbin, S. J., Turmukhambetov, D., & Brostow, G. J.
- Venue
- 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2017-07
- Pages
- 7168-7177
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2576915720
- Cited by
- 563
- References
- 6
- FWCI
- 18.04
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Harmonic Networks: Deep Translation and Rotation Equivariance. https://app.cochat.ai/papers/10.1109/cvpr.2017.758
- The paper
- Worrall, D. E., Garbin, S. J., Turmukhambetov, D., & Brostow, G. J. (2017). Harmonic Networks: Deep Translation and Rotation Equivariance. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr.2017.758
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
