Efficient 3D affinely equivariant CNNs with adaptive fusion of augmented spherical Fourier-Bessel bases

• URL: http://arxiv.org/abs/2402.16825v4
• Date: Wed, 11 Dec 2024 04:10:08 GMT
• Title: Efficient 3D affinely equivariant CNNs with adaptive fusion of augmented spherical Fourier-Bessel bases
• Authors: Wenzhao Zhao, Steffen Albert, Barbara D. Wichtmann, Angelika Maurer, Ulrike Attenberger, Frank G. Zöllner, Jürgen Hesser,
• Abstract summary: Filter-decomposition-based group equivariant convolutional neural networks (CNNs) have shown promising stability and data efficiency for 3D image feature extraction. This paper presents an efficient non- parameter-sharing continuous 3D affine group equivariant neural network for volumetric images.
• Score: 0.36122488107441414
• License:
• Abstract: Filter-decomposition-based group equivariant convolutional neural networks (CNNs) have shown promising stability and data efficiency for 3D image feature extraction. However, these networks, which rely on parameter sharing and discrete transformation groups, often underperform in modern deep neural network architectures for processing volumetric images, such as the common 3D medical images. To address these limitations, this paper presents an efficient non-parameter-sharing continuous 3D affine group equivariant neural network for volumetric images. This network uses an adaptive aggregation of Monte Carlo augmented spherical Fourier-Bessel filter bases to improve the efficiency and flexibility of 3D group equivariant CNNs for volumetric data. Unlike existing methods that focus only on angular orthogonality in filter bases, the introduced spherical Bessel Fourier filter base incorporates both angular and radial orthogonality to improve feature extraction. Experiments on four medical image segmentation datasets show that the proposed methods achieve better affine group equivariance and superior segmentation accuracy than existing 3D group equivariant convolutional neural network layers, significantly improving the training stability and data efficiency of conventional CNN layers (at 0.05 significance level). The code is available at https://github.com/ZhaoWenzhao/WMCSFB.

Related papers

• 3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction [50.07071392673984]
  Existing methods learn 3D rotations parametrized in the spatial domain using angles or quaternions. We propose a frequency-domain approach that directly predicts Wigner-D coefficients for 3D rotation regression. Our method achieves state-of-the-art results on benchmarks such as ModelNet10-SO(3) and PASCAL3D+.
  arXiv  Detail & Related papers  (2024-11-01T12:50:38Z)
• LeRF: Learning Resampling Function for Adaptive and Efficient Image Interpolation [64.34935748707673]
  Recent deep neural networks (DNNs) have made impressive progress in performance by introducing learned data priors. We propose a novel method of Learning Resampling (termed LeRF) which takes advantage of both the structural priors learned by DNNs and the locally continuous assumption. LeRF assigns spatially varying resampling functions to input image pixels and learns to predict the shapes of these resampling functions with a neural network.
  arXiv  Detail & Related papers  (2024-07-13T16:09:45Z)
• On the Fourier analysis in the SO(3) space : EquiLoPO Network [2.7624021966289605]
  Existing deep-learning approaches utilize either group convolutional networks limited to discrete rotations or steerable convolutional networks with constrained filter structures. This work proposes a novel equivariant neural network architecture that achieves analytical Equivariance to Local Pattern Orientation on the continuous SO(3) group. By integrating these operations into a ResNet-style architecture, we propose a model that overcomes the limitations of prior methods.
  arXiv  Detail & Related papers  (2024-04-24T16:54:39Z)
• Regular SE(3) Group Convolutions for Volumetric Medical Image Analysis [10.406659081400354]
  We devise a SE(3) group convolution kernel separated into a continuous SO(3) (rotation) kernel and a spatial kernel. Our approach achieves up to a 16.5% gain in accuracy over regular CNNs.
  arXiv  Detail & Related papers  (2023-06-24T13:29:54Z)
• Adaptive aggregation of Monte Carlo augmented decomposed filters for efficient group-equivariant convolutional neural network [0.36122488107441414]
  Group-equivariant convolutional neural networks (G-CNN) heavily rely on parameter sharing to increase CNN's data efficiency and performance. We propose a non- parameter-sharing approach for group equivariant neural networks. The proposed methods adaptively aggregate a diverse range of filters by a weighted sum of decomposedally augmented filters.
  arXiv  Detail & Related papers  (2023-05-17T10:18:02Z)
• Leveraging SO(3)-steerable convolutions for pose-robust semantic segmentation in 3D medical data [2.207533492015563]
  We present a new family of segmentation networks that use equivariant voxel convolutions based on spherical harmonics. These networks are robust to data poses not seen during training, and do not require rotation-based data augmentation during training. We demonstrate improved segmentation performance in MRI brain tumor and healthy brain structure segmentation tasks.
  arXiv  Detail & Related papers  (2023-03-01T09:27:08Z)
• Moving Frame Net: SE(3)-Equivariant Network for Volumes [0.0]
  A rotation and translation equivariant neural network for image data was proposed based on the moving frames approach. We significantly improve that approach by reducing the computation of moving frames to only one, at the input stage. Our trained model overperforms the benchmarks in the medical volume classification of most of the tested datasets from MedMNIST3D.
  arXiv  Detail & Related papers  (2022-11-07T10:25:38Z)
• CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation [95.51455777713092]
  Convolutional neural networks (CNNs) have been the de facto standard for nowadays 3D medical image segmentation. We propose a novel framework that efficiently bridges a bf Convolutional neural network and a bf Transformer bf (CoTr) for accurate 3D medical image segmentation.
  arXiv  Detail & Related papers  (2021-03-04T13:34:22Z)
• Spherical Transformer: Adapting Spherical Signal to CNNs [53.18482213611481]
  Spherical Transformer can transform spherical signals into vectors that can be directly processed by standard CNNs. We evaluate our approach on the tasks of spherical MNIST recognition, 3D object classification and omnidirectional image semantic segmentation.
  arXiv  Detail & Related papers  (2021-01-11T12:33:16Z)
• Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction [57.74609918453932]
  Automatic blood vessel extraction from 3D medical images is crucial for vascular disease diagnoses. Existing methods may suffer from discontinuities of extracted vessels when segmenting such thin tubular structures from 3D images. We argue that preserving the continuity of extracted vessels requires to take into account the global geometry. We propose a hybrid representation learning approach to address this challenge.
  arXiv  Detail & Related papers  (2020-12-14T05:22:49Z)
• Learning Local Neighboring Structure for Robust 3D Shape Representation [143.15904669246697]
  Representation learning for 3D meshes is important in many computer vision and graphics applications. We propose a local structure-aware anisotropic convolutional operation (LSA-Conv) Our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-21T13:40:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.