Deep Axial Hypercomplex Networks

• URL: http://arxiv.org/abs/2301.04626v1
• Date: Wed, 11 Jan 2023 18:31:00 GMT
• Title: Deep Axial Hypercomplex Networks
• Authors: Nazmul Shahadat, Anthony S. Maida
• Abstract summary: Recent works make it possible to improve representational capabilities by using hypercomplex-inspired networks. This paper reduces this cost by factorizing a quaternion 2D convolutional module into two consecutive vectormap 1D convolutional modules. Incorporating both yields our proposed hypercomplex network, a novel architecture that can be assembled to construct deep axial-hypercomplex networks.
• Score: 1.370633147306388
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Over the past decade, deep hypercomplex-inspired networks have enhanced feature extraction for image classification by enabling weight sharing across input channels. Recent works make it possible to improve representational capabilities by using hypercomplex-inspired networks which consume high computational costs. This paper reduces this cost by factorizing a quaternion 2D convolutional module into two consecutive vectormap 1D convolutional modules. Also, we use 5D parameterized hypercomplex multiplication based fully connected layers. Incorporating both yields our proposed hypercomplex network, a novel architecture that can be assembled to construct deep axial-hypercomplex networks (DANs) for image classifications. We conduct experiments on CIFAR benchmarks, SVHN, and Tiny ImageNet datasets and achieve better performance with fewer trainable parameters and FLOPS. Our proposed model achieves almost 2% higher performance for CIFAR and SVHN datasets, and more than 3% for the ImageNet-Tiny dataset and takes six times fewer parameters than the real-valued ResNets. Also, it shows state-of-the-art performance on CIFAR benchmarks in hypercomplex space.

Related papers

• DVMSR: Distillated Vision Mamba for Efficient Super-Resolution [7.551130027327461]
  We propose DVMSR, a novel lightweight Image SR network that incorporates Vision Mamba and a distillation strategy. Our proposed DVMSR can outperform state-of-the-art efficient SR methods in terms of model parameters.
  arXiv  Detail & Related papers  (2024-05-05T17:34:38Z)
• ESDMR-Net: A Lightweight Network With Expand-Squeeze and Dual Multiscale Residual Connections for Medical Image Segmentation [7.921517156237902]
  This paper presents an expand-squeeze dual multiscale residual network ( ESDMR-Net) It is a fully convolutional network that is well-suited for resource-constrained computing hardware such as mobile devices. We present experiments on seven datasets from five distinct examples of applications.
  arXiv  Detail & Related papers  (2023-12-17T02:15:49Z)
• Enhancing ResNet Image Classification Performance by using Parameterized Hypercomplex Multiplication [1.370633147306388]
  This paper studies ResNet architectures and incorporates parameterized hypercomplex multiplication into the backend of residual, quaternion, and vectormap convolutional neural networks to assess the effect. We show that PHM does improve classification accuracy performance on several image datasets, including small, low-resolution CIFAR 10/100 and large high-resolution ImageNet and ASL, and can achieve state-of-the-art accuracy for hypercomplex networks.
  arXiv  Detail & Related papers  (2023-01-11T18:24:07Z)
• Hypercomplex Image-to-Image Translation [13.483068375377362]
  Image-to-image translation (I2I) aims at transferring the content representation from an input domain to an output one. Recent I2I generative models, which gain outstanding results in this task, comprise a set of diverse deep networks each with tens of million parameters. We propose to leverage hypercomplex algebra properties to define lightweight I2I generative models capable of preserving pre-existing relations among image dimensions.
  arXiv  Detail & Related papers  (2022-05-04T14:28:50Z)
• Hybrid Pixel-Unshuffled Network for Lightweight Image Super-Resolution [64.54162195322246]
  Convolutional neural network (CNN) has achieved great success on image super-resolution (SR) Most deep CNN-based SR models take massive computations to obtain high performance. We propose a novel Hybrid Pixel-Unshuffled Network (HPUN) by introducing an efficient and effective downsampling module into the SR task.
  arXiv  Detail & Related papers  (2022-03-16T20:10:41Z)
• A New Backbone for Hyperspectral Image Reconstruction [90.48427561874402]
  3D hyperspectral image (HSI) reconstruction refers to inverse process of snapshot compressive imaging. Proposal is for a Spatial/Spectral Invariant Residual U-Net, namely SSI-ResU-Net. We show that SSI-ResU-Net achieves competing performance with over 77.3% reduction in terms of floating-point operations.
  arXiv  Detail & Related papers  (2021-08-17T16:20:51Z)
• CondenseNet V2: Sparse Feature Reactivation for Deep Networks [87.38447745642479]
  Reusing features in deep networks through dense connectivity is an effective way to achieve high computational efficiency. We propose an alternative approach named sparse feature reactivation (SFR), aiming at actively increasing the utility of features for reusing. Our experiments show that the proposed models achieve promising performance on image classification (ImageNet and CIFAR) and object detection (MS COCO) in terms of both theoretical efficiency and practical speed.
  arXiv  Detail & Related papers  (2021-04-09T14:12:43Z)
• Learning Frequency-aware Dynamic Network for Efficient Super-Resolution [56.98668484450857]
  This paper explores a novel frequency-aware dynamic network for dividing the input into multiple parts according to its coefficients in the discrete cosine transform (DCT) domain. In practice, the high-frequency part will be processed using expensive operations and the lower-frequency part is assigned with cheap operations to relieve the computation burden. Experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures.
  arXiv  Detail & Related papers  (2021-03-15T12:54:26Z)
• Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning [73.75457731689858]
  We develop a computation efficient yet accurate network based on the proposed attentive auxiliary features (A$2$F) for SISR. Experimental results on large-scale dataset demonstrate the effectiveness of the proposed model against the state-of-the-art (SOTA) SR methods.
  arXiv  Detail & Related papers  (2020-11-13T06:01:46Z)
• Real Image Super Resolution Via Heterogeneous Model Ensemble using GP-NAS [63.48801313087118]
  We propose a new method for image superresolution using deep residual network with dense skip connections. The proposed method won the first place in all three tracks of the AIM 2020 Real Image Super-Resolution Challenge.
  arXiv  Detail & Related papers  (2020-09-02T22:33:23Z)

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.