← Back to all news
arXiv Computer Vision By Bryce Grant, Peng Wang

Quaternion Approximate Networks for Enhanced Image Classification and Oriented Object Detection

Read the original on arXiv Computer Vision →

Quaternion Approximate Networks (QUAN) is a deep learning framework that uses quaternion algebra to achieve rotation equivariant image classification and object detection. QUAN approximates quaternion convolution via Hamilton product decomposition with real-valued operations, enabling efficient CUDA implementation and preserving geometric properties. The method introduces Independent Quaternion Batch Normalization and extends quaternion operations to spatial attention, achieving higher accuracy, faster convergence, and improved parameter efficiency on CIFAR, ImageNet, COCO, and DOTA benchmarks compared to conventional CNNs and other quaternion models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Oct 27

ACSAN: All-Convolutional Self-Attention Network Integrating Convolutional Operations with Vision Transformer

The paper introduces ACSAN, an All‑Convolutional Self‑Attention Network that replaces the fully‑connected matrix multiplications of Vision Transformers with convolution operations. Its core module, Dynamic Convolutional Self‑Attention (DCSA), uses multi‑scale dilated convolutions to produce Query, Key, and Value tensors, and combines spatial and channel self‑attention into a single output. Experiments on CIFAR‑10, CIFAR‑100, and ImageNet‑1k demonstrate that ACSAN attains competitive or superior classification accuracy to ViT while using comparable or fewer parameters, and ablation studies confirm the positive contribution of each component.

By Zimian Wei, Tianqi Zhang, Hengyue Pan
llmscomputer-visionbenchmarks
More like this →
Hugging Face Trending Papers
Aug 7

Classical $\mathrm{SU}(2)$ Models Match or Exceed Shallow Variational Quantum Circuits on Vision Benchmarks

Quaternion-valued neural networks and variational quantum circuits (VQCs) both derive local transformations from $\mathrm{SU}(2)$ geometry, yet their performance on classical supervised learning remains poorly understood. We compare real-valued, quaternion-valued, and quantum classification heads on identical frozen features across MNIST, FashionMNIST, and CIFAR-10.

benchmarkssafety
More like this →
arXiv Machine Learning
Jul 22

Recti-Q: Feature-Space Rectification for Out-of-Distribution-Robust Quantized Perception in Edge Robotics

arXiv:2607. 18540v1 Announce Type: cross Abstract: Robotic perception pipelines increasingly rely on large vision backbones deployed on SWaP-constrained edge platforms, making post-training quantization (PTQ) attractive for real-time inference.

By Hamidreza Yaghoubi Araghi, Parastoo Pilevar, Ming C. Lin
llmsroboticsfine-tuningefficiencybenchmarks
More like this →
arXiv Machine Learning
Aug 11

Classical $\mathrm{SU}(2)$ Models Match or Exceed Shallow Variational Quantum Circuits on Vision Benchmarks

arXiv:2608. 07822v1 Announce Type: cross Abstract: Quaternion-valued neural networks and variational quantum circuits (VQCs) both derive local transformations from $\mathrm{SU}(2)$ geometry, yet their performance on classical supervised learning remains poorly understood.

By Christopher Fulton, Irene Tsapara, Lawrence Fulton
benchmarkssafety
More like this →
Hugging Face Trending Papers
Aug 5

Image Classification Using CNN-QNN Hybrid Model with Optimized Correlated Features

We propose a method to optimize the correlation among convolutional neural network (CNN) features that are used as inputs to quantum neural network (QNN) to enhance image classification accuracy. Unlike prior approaches that employ orthogonal decomposition as preprocessing, we intentionally introduce correlated features that are more physically compatible with QNN.

computer-visionrobotics
More like this →