paper-with-me

홈 › Papers

Equivariant Filters for Efficient Tracking in 3D Imaging

2021-03-18 · Daniel Moyer, Esra Abaci Turk, P Ellen Grant, William M. Wells, Polina Golland

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.

📄 PDF Abstract BibTeX arXiv:2103.10255

Code (0)

등록된 구현이 없습니다.

Tasks

Object Tracking

Similar Papers 제목 키워드 기반

Rotation Equivariant Siamese Networks for Tracking

2020-12-24 · CVPR 2021 1 · Deepak K. Gupta, Devanshu Arya, Efstratios Gavves

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+1

SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRI

2023-12-21 · Benjamin Billot, Neel Dey, Daniel Moyer, Malte Hoffmann 외

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 Series

SpaER: Learning Spatio-temporal Equivariant Representations for Fetal Brain Motion Tracking

2024-07-29 · Jian Wang, Razieh Faghihpirayesh, Polina Golland, Ali Gholipour

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 Augmentation

Rotation-Scale Equivariant Steerable Filters

2023-04-10 · Yilong Yang, Srinandan Dasmahapatra, Sasan Mahmoodi

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…

GPU

Scale-Equivariant Neural Networks with Decomposed Convolutional Filters

2019-09-25 · Wei Zhu, Qiang Qiu, Robert Calderbank, Guillermo Sapiro 외

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