# Rotation Equivariant Siamese Networks for Tracking

arXiv: https://arxiv.org/abs/2012.13078 · HTML: https://mlsanity.com/paper/2012.13078/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2020.

## Built on by (most cited first, 15 of 15)

- [Leveraging Equivariant Features for Absolute Pose Regression](https://mlsanity.com/paper/2204.02163/) (2022)
- [Reflection and Rotation Symmetry Detection via Equivariant Learning](https://mlsanity.com/paper/2203.16787/) (2022)
- [Normalization-Equivariant Neural Networks with Application to Image Denoising](https://mlsanity.com/paper/2306.05037/) (2023)
- [Homography Decomposition Networks for Planar Object Tracking](https://mlsanity.com/paper/2112.07909/) (2021)
- [Robust Perception through Equivariance](https://mlsanity.com/paper/2212.06079/) (2022)
- [FRED: Towards a Full Rotation-Equivariance in Aerial Image Object Detection](https://mlsanity.com/paper/2401.06159/) (2023)
- [Implicit Equivariance in Convolutional Networks](https://mlsanity.com/paper/2111.14157/) (2021)
- [A Discriminative Single-Shot Segmentation Network for Visual Object Tracking](https://mlsanity.com/paper/2112.11846/) (2021)
- [SRE-CNN: A Spatiotemporal Rotation-Equivariant CNN for Cardiac Cine MR Imaging](https://mlsanity.com/paper/2409.08537/) (2024)
- [On normalization-equivariance properties of supervised and unsupervised denoising methods: a survey](https://mlsanity.com/paper/2402.15352/) (2024)
- [PreCM: The Padding-based Rotation Equivariant Convolution Mode for Semantic Segmentation](https://mlsanity.com/paper/2411.01624/) (2024)
- [GMR-Conv: An Efficient Rotation and Reflection Equivariant Convolution Kernel Using Gaussian Mixture Rings](https://mlsanity.com/paper/2504.02819/) (2025)
- [Flow Equivariant Recurrent Neural Networks](https://mlsanity.com/paper/2507.14793/) (2025)
- [Rotation Equivariant 3D Hand Mesh Generation from a Single RGB Image](https://mlsanity.com/paper/2111.13023/) (2021)
- [Equivariant Imaging Biomarkers for Robust Unsupervised Segmentation of Histopathology](https://mlsanity.com/paper/2505.05689/) (2025)

## Abstract (arXiv)

Rotation is among the long prevailing, yet still unresolved, hard challenges encountered in visual object tracking. The existing deep learning-based tracking algorithms use regular CNNs that are inherently translation equivariant, but not designed to tackle rotations. In this paper, we first demonstrate that in the presence of rotation instances in videos, the performance of existing trackers is severely affected. To circumvent the adverse effect of rotations, we present rotation-equivariant Siamese networks (RE-SiamNets), built through the use of group-equivariant convolutional layers comprising steerable filters. SiamNets allow estimating the change in orientation of the object in an unsupervised manner, thereby facilitating its use in relative 2D pose estimation as well. We further show that this change in orientation can be used to impose an additional motion constraint in Siamese tracking through imposing restriction on the change in orientation between two consecutive frames. For benchmarking, we present Rotation Tracking Benchmark (RTB), a dataset comprising a set of videos with rotation instances. Through experiments on two popular Siamese architectures, we show that RE-SiamNets handle the problem of rotation very well and out-perform their regular counterparts. Further, RE-SiamNets can accurately estimate the relative change in pose of the target in an unsupervised fashion, namely the in-plane rotation the target has sustained with respect to the reference frame.