Search
Search Results
-
Response index: quantitative evaluation index of translational equivariance
Translational equivariance, one of the properties of Convolutional neural networks(CNNs), directly reflects the coherence of the influence of input...
-
Rotation invariance and equivariance in 3D deep learning: a survey
Deep neural networks (DNNs) in 3D scenes show a strong capability of extracting high-level semantic features and significantly promote research in...
-
Generalization in Deep RL for TSP Problems via Equivariance and Local Search
Deep reinforcement learning (RL) has proved to be a competitive heuristic for solving small-sized instances of traveling salesman problems (TSP), but...
-
Self Supervised Contrastive Learning Combining Equivariance and Invariance
Current self-supervised representation learning methods are mainly based on contrastive learning and proxy tasks. These methods acquire semantically...
-
Learning Temporally Equivariance for Degenerative Disease Progression in OCT by Predicting Future Representations
Contrastive pretraining provides robust representations by ensuring their invariance to different image transformations while simultaneously...
-
Convolution Filter Equivariance/Invariance in Convolutional Neural Networks: A Survey
Models parameterized by Convolutional Neural Networks (CNNs), reportedly, have garnered a commanding position in learning based multidimensional...
-
Equivariance-Based Analysis of PDE Evolutions Related to Multivariate Medians
For multivariate data there exist several concepts generalising the median, which differ by their equivariance properties w.r.t. transformations of...
-
Equivariance and Invariance Inductive Bias for Learning from Insufficient Data
We are interested in learning robust models from insufficient data, without the need for any externally pre-trained checkpoints. First, compared to...
-
Equivariant Spatio-temporal Self-supervision for LiDAR Object Detection
Popular representation learning methods encourage feature invariance under transformations applied at the input. However, in 3D perception tasks like...
-
Using scale-equivariant CNN to enhance scale robustness in feature matching
Image matching is an important task in computer vision. The detector-free dense matching method is an important research direction of image matching...
-
SOE: SO(3)-Equivariant 3D MRI Encoding
Representation learning has become increasingly important, especially as powerful models have shifted towards learning latent representations before...
-
Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration
Point cloud registration is a foundational task for 3D alignment and reconstruction applications. While both traditional and learning-based...
-
Regular SE(3) Group Convolutions for Volumetric Medical Image Analysis
Regular group convolutional neural networks (G-CNNs) have been shown to increase model performance and improve equivariance to different geometrical...
-
GM-GAN: Geometric Generative Models Based on Morphological Equivariant PDEs and GANs
This work deals with image generation, two main problems are addressed: (i) improvements of specific feature extraction while accounting at...
-
Unsupervised Low-Light Image Enhancement via Spectral Consistency
Retinex-based unsupervised low-light enhancement methods have demonstrated notable performance without paired data. However, existing Retinex-based...
-
Rotation-equivariant spherical vector networks for objects recognition with unknown poses
Analyzing 3D objects without pose priors using neural networks is challenging. In view of the shortcoming that spherical convolutional networks lack...
-
Revisiting Consistency Regularization for Semi-Supervised Learning
Consistency regularization is one of the most widely-used techniques for semi-supervised learning (SSL). Generally, the aim is to train a model that...
-
\({{\,\textrm{SL}\,}}(2,\mathbb {Z})\) -Equivariant Machine Learning with Modular Forms Theory and Applications
This paper introduces an approach for building Machine Learning (ML) algorithms embedding equivariance mechanisms to the Lie group...
-
Group Equivariant Networks Using Morphological Operators
With the increase of interest upon rotation invariance and equivariance for Convolutional Neural Network (CNN), a fair amount of papers have been...
-
SIM2E: Benchmarking the Group Equivariant Capability of Correspondence Matching Algorithms
Correspondence matching is a fundamental problem in computer vision and robotics applications. Solving correspondence matching problems using neural...