Quaternion Approximation Networks for Enhanced Image Classification and Oriented Object Detection

• URL: http://arxiv.org/abs/2509.05512v1
• Date: Fri, 05 Sep 2025 21:41:40 GMT
• Title: Quaternion Approximation Networks for Enhanced Image Classification and Oriented Object Detection
• Authors: Bryce Grant, Peng Wang,
• Abstract summary: Quaternion Approximate Networks (QUAN) is a novel deep learning framework that leverages quaternion algebra for rotation equivariant image classification and object detection.<n>Quaternion Approximate Networks (QUAN) is evaluated on image classification (CIFAR-10/100, ImageNet), object detection (COCO, DOTA), and robotic perception tasks.<n>These results highlight its potential for deployment in resource-constrained robotic systems requiring rotation-aware perception and application in other domains.
• Score: 2.847742374860449
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces Quaternion Approximate Networks (QUAN), a novel deep learning framework that leverages quaternion algebra for rotation equivariant image classification and object detection. Unlike conventional quaternion neural networks attempting to operate entirely in the quaternion domain, QUAN approximates quaternion convolution through Hamilton product decomposition using real-valued operations. This approach preserves geometric properties while enabling efficient implementation with custom CUDA kernels. We introduce Independent Quaternion Batch Normalization (IQBN) for training stability and extend quaternion operations to spatial attention mechanisms. QUAN is evaluated on image classification (CIFAR-10/100, ImageNet), object detection (COCO, DOTA), and robotic perception tasks. In classification tasks, QUAN achieves higher accuracy with fewer parameters and faster convergence compared to existing convolution and quaternion-based models. For objection detection, QUAN demonstrates improved parameter efficiency and rotation handling over standard Convolutional Neural Networks (CNNs) while establishing the SOTA for quaternion CNNs in this downstream task. These results highlight its potential for deployment in resource-constrained robotic systems requiring rotation-aware perception and application in other domains.

Related papers

• K-DAREK: Distance Aware Error for Kurkova Kolmogorov Networks [3.460138063155115]
  We develop a novel learning algorithm, distance-aware error for Kurkova-Kolmogorov networks (K-DAREK), for efficient and interpretable function approximation with uncertainty quantification.<n>Our approach establishes robust error bounds that are distance-aware; this means they reflect the proximity of a test point to its nearest training points.
  arXiv  Detail & Related papers  (2025-10-24T20:49:59Z)
• Asymptotically Stable Quaternion-valued Hopfield-structured Neural Network with Periodic Projection-based Supervised Learning Rules [3.869763264003111]
  We propose a quaternion-valued supervised learning Hopfield-structured neural network (QSHNN) with a fully connected structure inspired by the classic Hopfield neural network (HNN)<n>For the learning rules, we introduce a periodic projection strategy that modifies standard descent by periodically projecting each 4*4 block of the weight matrix onto the closest quaternionic structure in the least-squares sense.<n>Benefiting from this rigorous mathematical foundation, the experimental model implementation achieves high accuracy, fast convergence, and strong reliability across randomly generated target sets.
  arXiv  Detail & Related papers  (2025-10-18T18:10:07Z)
• Exploring Kernel Transformations for Implicit Neural Representations [57.2225355625268]
  Implicit neural representations (INRs) leverage neural networks to represent signals by mapping coordinates to their corresponding attributes.<n>This work pioneers the exploration of the effect of kernel transformation of input/output while keeping the model itself unchanged.<n>A byproduct of our findings is a simple yet effective method that combines scale and shift to significantly boost INR with negligible overhead.
  arXiv  Detail & Related papers  (2025-04-07T04:43:50Z)
• Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware [78.17783007774295]
  This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval.<n>A novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed.<n>The converted SNNs achieve almost five-fold power efficiency at moderate performance loss compared to the original CNNs.
  arXiv  Detail & Related papers  (2024-12-05T09:41:33Z)
• Quanv4EO: Empowering Earth Observation by means of Quanvolutional Neural Networks [62.12107686529827]
  This article highlights a significant shift towards leveraging quantum computing techniques in processing large volumes of remote sensing data. The proposed Quanv4EO model introduces a quanvolution method for preprocessing multi-dimensional EO data. Key findings suggest that the proposed model not only maintains high precision in image classification but also shows improvements of around 5% in EO use cases.
  arXiv  Detail & Related papers  (2024-07-24T09:11:34Z)
• DCNN: Dual Cross-current Neural Networks Realized Using An Interactive Deep Learning Discriminator for Fine-grained Objects [48.65846477275723]
  This study proposes novel dual-current neural networks (DCNN) to improve the accuracy of fine-grained image classification. The main novel design features for constructing a weakly supervised learning backbone model DCNN include (a) extracting heterogeneous data, (b) keeping the feature map resolution unchanged, (c) expanding the receptive field, and (d) fusing global representations and local features.
  arXiv  Detail & Related papers  (2024-05-07T07:51:28Z)
• Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation [33.88445464404075]
  Few-shot segmentation (FSS) aims to segment unseen classes given only a few samples. We introduce a quaternion perspective on correlation learning and propose a novel Quaternion-valued Correlation Learning Network (QCLNet) Our QCLNet is formulated as a hyper-complex valued network and represents correlation tensors in the quaternion domain, which uses quaternion-valued convolution to explore the external relations of query subspace.
  arXiv  Detail & Related papers  (2023-05-12T06:56:22Z)
• A Neural Network-enhanced Reproducing Kernel Particle Method for Modeling Strain Localization [0.0]
  In this work, neural network-enhanced reproducing kernel particle method (NN-RKPM) is proposed. The location, orientation, and shape of the solution transition near a localization is automatically captured by the NN approximation. The effectiveness of the proposed NN-RKPM is verified by a series of numerical verifications.
  arXiv  Detail & Related papers  (2022-04-28T23:59:38Z)
• Inducing Gaussian Process Networks [80.40892394020797]
  We propose inducing Gaussian process networks (IGN), a simple framework for simultaneously learning the feature space as well as the inducing points. The inducing points, in particular, are learned directly in the feature space, enabling a seamless representation of complex structured domains. We report on experimental results for real-world data sets showing that IGNs provide significant advances over state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-21T05:27:09Z)
• A Quaternion-Valued Variational Autoencoder [15.153617649974263]
  variational autoencoders (VAEs) have proved their ability in modeling a generative process by learning a latent representation of the input. We propose a novel VAE defined in the quaternion domain, which exploits the properties of quaternion algebra to improve performance.
  arXiv  Detail & Related papers  (2020-10-22T12:33:42Z)
• Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks [54.27962244835622]
  This paper proposes a new mean-field framework for over- parameterized deep neural networks (DNNs) In this framework, a DNN is represented by probability measures and functions over its features in the continuous limit. We illustrate the framework via the standard DNN and the Residual Network (Res-Net) architectures.
  arXiv  Detail & Related papers  (2020-07-03T01:37:16Z)

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.