No article text was recorded for this version.
directional information loss (invariance-performance trade-off)
Version 1 of 125 papers32 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Learning Rotation-Agnostic Representations via Group Equivariant VAEs
- Blog: Equivariant Point Network for 3D Point Cloud Analysis
- Blog: Effective Rotation-Invariant Point CNN with Spherical Harmonics Kernels
- Blog: RIC-CNN: Rotation-Invariant Coordinate Convolutional Neural Network
- Blog: E(n) Equivariant Graph Neural Networks
- Blog: Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination
- Blog: Rotation Invariant Convolutions for 3D Point Clouds Deep Learning
- Blog: Orientation Covariant Aggregation of Local Descriptors with Embeddings
- Blog: Multi-directional geodesic neural networks via equivariant convolution
- Blog: Geodesic Convolutional Neural Networks on Riemannian Manifolds
- Blog: Learning Steerable Function for Efficient Image Resampling
- Blog: A Functional Approach to Rotation Equivariant Non-Linearities for Tensor Field Networks
- Blog: SRE-Conv: Symmetric Rotation Equivariant Convolution for Biomedical Image Classification
- Blog: TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis
- Blog: 3D Local Features for Direct Pairwise Registration
- Blog: A new approach to observational cosmology using the scattering transform
- Blog: Combined scattering for rotation invariant texture analysis
- Blog: Rotation Equivariant Vector Field Networks
- Blog: MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding
- Blog: A Rotation-Invariant Framework for Deep Point Cloud Analysis
- Blog: RISurConv: Rotation Invariant Surface Attention-Augmented Convolutions for 3D Point Cloud Classification and Segmentation
- Blog: CNNs on Surfaces using Rotation-Equivariant Features
- Blog: ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation
- Blog: Regular SE(3) Group Convolutions for Volumetric Medical Image Analysis
- Blog: Local rotation invariance in 3D CNNs
History & citation
Current · Permanent link
- This direction split from Preserving Directional Information in Rotation Invariant Models (60% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_directional_information_loss_invariance__b8ff6559,
title = {directional information loss (invariance-performance trade-off)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/directional-information-loss-invariance-performance-trade-off/rdr_b8ff6559e95f4b2e9112cfdab0ff3b89},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_directional_information_loss_invariance__b8ff6559_v1,
title = {directional information loss (invariance-performance trade-off)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/directional-information-loss-invariance-performance-trade-off/rdr_b8ff6559e95f4b2e9112cfdab0ff3b89/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}