DreamNet: A Deep Riemannian Network based on SPD Manifold Learning for Visual Classification

• URL: http://arxiv.org/abs/2206.07967v1
• Date: Thu, 16 Jun 2022 07:15:20 GMT
• Title: DreamNet: A Deep Riemannian Network based on SPD Manifold Learning for Visual Classification
• Authors: Rui Wang, Xiao-Jun Wu, Ziheng Chen, Tianyang Xu, Josef Kittler
• Abstract summary: We propose a new architecture for SPD matrix learning. To enrich the deep representations, we adopt SPDNet as the backbone. We then insert several residual-like blocks with shortcut connections to augment the representational capacity of SRAE.
• Score: 36.848148506610364
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image set-based visual classification methods have achieved remarkable performance, via characterising the image set in terms of a non-singular covariance matrix on a symmetric positive definite (SPD) manifold. To adapt to complicated visual scenarios better, several Riemannian networks (RiemNets) for SPD matrix nonlinear processing have recently been studied. However, it is pertinent to ask, whether greater accuracy gains can be achieved by simply increasing the depth of RiemNets. The answer appears to be negative, as deeper RiemNets tend to lose generalization ability. To explore a possible solution to this issue, we propose a new architecture for SPD matrix learning. Specifically, to enrich the deep representations, we adopt SPDNet [1] as the backbone, with a stacked Riemannian autoencoder (SRAE) built on the tail. The associated reconstruction error term can make the embedding functions of both SRAE and of each RAE an approximate identity mapping, which helps to prevent the degradation of statistical information. We then insert several residual-like blocks with shortcut connections to augment the representational capacity of SRAE, and to simplify the training of a deeper network. The experimental evidence demonstrates that our DreamNet can achieve improved accuracy with increased depth of the network.

Related papers

• 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)
• Differentiable Neural Networks with RePU Activation: with Applications to Score Estimation and Isotonic Regression [7.450181695527364]
  We study the properties of differentiable neural networks activated by rectified power unit (RePU) functions. We establish error bounds for simultaneously approximating $Cs$ smooth functions and their derivatives using RePU-activated deep neural networks.
  arXiv  Detail & Related papers  (2023-05-01T00:09:48Z)
• Singular Value Perturbation and Deep Network Optimization [29.204852309828006]
  We develop new theoretical results on matrix perturbation to shed light on the impact of architecture on the performance of a deep network. In particular, we explain what deep learning practitioners have long observed empirically: the parameters of some deep architectures are easier to optimize than others. A direct application of our perturbation results explains analytically why a ResNet is easier to optimize than a ConvNet.
  arXiv  Detail & Related papers  (2022-03-07T02:09:39Z)
• A Deeper Look into Convolutions via Pruning [9.89901717499058]
  Modern architectures contain a very small number of fully-connected layers, often at the end, after multiple layers of convolutions. Although this strategy already reduces the number of parameters, most of the convolutions can be eliminated as well, without suffering any loss in recognition performance. In this work, we use the matrix characteristics based on eigenvalues in addition to the classical weight-based importance assignment approach for pruning to shed light on the internal mechanisms of a widely used family of CNNs.
  arXiv  Detail & Related papers  (2021-02-04T18:55:03Z)
• Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image Restoration [65.11022516031463]
  We present a deep interleaved network (DIN) that learns how information at different states should be combined for high-quality (HQ) images reconstruction. In this paper, we propose asymmetric co-attention (AsyCA) which is attached at each interleaved node to model the feature dependencies. Our presented DIN can be trained end-to-end and applied to various image restoration tasks.
  arXiv  Detail & Related papers  (2020-10-29T15:32:00Z)
• Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [78.65792427542672]
  Dynamic Graph Network (DG-Net) is a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent connection paths. Instead of using the same path of the network, DG-Net aggregates features dynamically in each node, which allows the network to have more representation ability.
  arXiv  Detail & Related papers  (2020-10-02T16:50:26Z)
• Adaptive Context-Aware Multi-Modal Network for Depth Completion [107.15344488719322]
  We propose to adopt the graph propagation to capture the observed spatial contexts. We then apply the attention mechanism on the propagation, which encourages the network to model the contextual information adaptively. Finally, we introduce the symmetric gated fusion strategy to exploit the extracted multi-modal features effectively. Our model, named Adaptive Context-Aware Multi-Modal Network (ACMNet), achieves the state-of-the-art performance on two benchmarks.
  arXiv  Detail & Related papers  (2020-08-25T06:00:06Z)
• Deep Adaptive Inference Networks for Single Image Super-Resolution [72.7304455761067]
  Single image super-resolution (SISR) has witnessed tremendous progress in recent years owing to the deployment of deep convolutional neural networks (CNNs) In this paper, we take a step forward to address this issue by leveraging the adaptive inference networks for deep SISR (AdaDSR) Our AdaDSR involves an SISR model as backbone and a lightweight adapter module which takes image features and resource constraint as input and predicts a map of local network depth.
  arXiv  Detail & Related papers  (2020-04-08T10:08:20Z)
• Deep Residual-Dense Lattice Network for Speech Enhancement [29.53125031648651]
  Convolutional neural networks (CNNs) with residual links (ResNets) and causal dilated convolutional units have been the network of choice for deep learning approaches to speech enhancement. One strategy to improve feature re-usage is to fuse both ResNets and densely connected CNNs (DenseNets) We propose the residual-dense lattice network (RDL-Net), which employs both residual and dense aggregations without over-allocating parameters for feature re-usage.
  arXiv  Detail & Related papers  (2020-02-27T04:36:30Z)

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.