Riemannian Self-Attention Mechanism for SPD Networks

• URL: http://arxiv.org/abs/2311.16738v1
• Date: Tue, 28 Nov 2023 12:34:46 GMT
• Title: Riemannian Self-Attention Mechanism for SPD Networks
• Authors: Rui Wang, Xiao-Jun Wu, Hui Li, Josef Kittler
• Abstract summary: An SPD manifold self-attention mechanism (SMSA) is proposed in this paper. An SMSA-based geometric learning module (SMSA-GL) is designed for the sake of improving the discrimination of structured representations.
• Score: 34.794770395408335
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Symmetric positive definite (SPD) matrix has been demonstrated to be an effective feature descriptor in many scientific areas, as it can encode spatiotemporal statistics of the data adequately on a curved Riemannian manifold, i.e., SPD manifold. Although there are many different ways to design network architectures for SPD matrix nonlinear learning, very few solutions explicitly mine the geometrical dependencies of features at different layers. Motivated by the great success of self-attention mechanism in capturing long-range relationships, an SPD manifold self-attention mechanism (SMSA) is proposed in this paper using some manifold-valued geometric operations, mainly the Riemannian metric, Riemannian mean, and Riemannian optimization. Then, an SMSA-based geometric learning module (SMSA-GLM) is designed for the sake of improving the discrimination of the generated deep structured representations. Extensive experimental results achieved on three benchmarking datasets show that our modification against the baseline network further alleviates the information degradation problem and leads to improved accuracy.

Related papers

• RMLR: Extending Multinomial Logistic Regression into General Geometries [64.16104856124029]
  Our framework only requires minimal geometric properties, thus exhibiting broad applicability. We develop five families of SPD MLRs under five types of power-deformed metrics. On rotation matrices we propose Lie MLR based on the popular bi-invariant metric.
  arXiv  Detail & Related papers  (2024-09-28T18:38:21Z)
• Riemannian Multinomial Logistics Regression for SPD Neural Networks [60.11063972538648]
  We propose a new type of deep neural network for Symmetric Positive Definite (SPD) matrices. Our framework offers a novel intrinsic explanation for the most popular LogEig classifier in existing SPD networks. The effectiveness of our method is demonstrated in three applications: radar recognition, human action recognition, and electroencephalography (EEG) classification.
  arXiv  Detail & Related papers  (2023-05-18T20:12:22Z)
• Adaptive Log-Euclidean Metrics for SPD Matrix Learning [73.12655932115881]
  We propose Adaptive Log-Euclidean Metrics (ALEMs), which extend the widely used Log-Euclidean Metric (LEM) The experimental and theoretical results demonstrate the merit of the proposed metrics in improving the performance of SPD neural networks.
  arXiv  Detail & Related papers  (2023-03-26T18:31:52Z)
• A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifold [7.737713458418288]
  Deep Learning (DL) has achieved success in complex Artificial Intelligence (AI) tasks, but it suffers from various notorious problems. This article presents a comprehensive survey of applying geometric optimization in DL. It investigates the application of geometric optimization in different DL networks in various AI tasks, e.g., convolution neural network, recurrent neural network, transfer learning, and optimal transport.
  arXiv  Detail & Related papers  (2023-02-16T10:50:15Z)
• Exploiting Temporal Structures of Cyclostationary Signals for Data-Driven Single-Channel Source Separation [98.95383921866096]
  We study the problem of single-channel source separation (SCSS) We focus on cyclostationary signals, which are particularly suitable in a variety of application domains. We propose a deep learning approach using a U-Net architecture, which is competitive with the minimum MSE estimator.
  arXiv  Detail & Related papers  (2022-08-22T14:04:56Z)
• Riemannian Local Mechanism for SPD Neural Networks [43.789561494266316]
  We argue that it is of utmost importance to ensure the preservation of local geometric information in SPD networks. We first analyse the convolution operator commonly used for capturing local information in Euclidean deep networks. Based on this analysis, we define the local information in the SPD manifold and design a multi-scale submanifold block for mining local geometry.
  arXiv  Detail & Related papers  (2022-01-25T07:39:25Z)
• GenURL: A General Framework for Unsupervised Representation Learning [58.59752389815001]
  Unsupervised representation learning (URL) learns compact embeddings of high-dimensional data without supervision. We propose a unified similarity-based URL framework, GenURL, which can smoothly adapt to various URL tasks. Experiments demonstrate that GenURL achieves consistent state-of-the-art performance in self-supervised visual learning, unsupervised knowledge distillation (KD), graph embeddings (GE), and dimension reduction.
  arXiv  Detail & Related papers  (2021-10-27T16:24:39Z)
• ResNet-LDDMM: Advancing the LDDMM Framework Using Deep Residual Networks [86.37110868126548]
  In this work, we make use of deep residual neural networks to solve the non-stationary ODE (flow equation) based on a Euler's discretization scheme. We illustrate these ideas on diverse registration problems of 3D shapes under complex topology-preserving transformations.
  arXiv  Detail & Related papers  (2021-02-16T04:07:13Z)

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.