Equivariant Filters for Efficient Tracking in 3D Imaging
We demonstrate an object tracking method for 3D images with fixed computational cost and state-of-the-art performance. Previous methods predicted transformation parameters from convolutional layers. We instead propose an architecture that does not include either flattening of convolutional features or fully connected layers, but instead relies on equivariant filters to preserve transformations between inputs and outputs (e.g. rot./trans. of inputs rotate/translate outputs). The transformation is then derived in closed form from the outputs of the filters. This method is useful for applications requiring low latency, such as real-time tracking. We demonstrate our model on synthetically augmented adult brain MRI, as well as fetal brain MRI, which is the intended use-case.
Code (0)
등록된 구현이 없습니다.
Tasks
Object TrackingSimilar Papers 제목 키워드 기반
Rotation Equivariant Siamese Networks for Tracking
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 eq…
2D Pose EstimationBenchmarkingObject TrackingPose Estimation+1SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRI
Rigid motion tracking is paramount in many medical imaging applications where movements need to be detected, corrected, or accounted for. Modern strategies rely on convolutional neural networks (CNN) and pose this proble…
Time SeriesSpaER: Learning Spatio-temporal Equivariant Representations for Fetal Brain Motion Tracking
In this paper, we introduce SpaER, a pioneering method for fetal motion tracking that leverages equivariant filters and self-attention mechanisms to effectively learn spatio-temporal representations. Different from conve…
Data AugmentationRotation-Scale Equivariant Steerable Filters
Incorporating either rotation equivariance or scale equivariance into CNNs has proved to be effective in improving models' generalization performance. However, jointly integrating rotation and scale equivariance into CNN…
GPUScale-Equivariant Neural Networks with Decomposed Convolutional Filters
Encoding the input scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many vision tasks especially when dealing with multiscale input signals. We study,…
image-classificationImage Classification