# QUAN: Quaternion Approximate Networks Improve Image Classification and Oriented Object Detection

- Source: HuggingFace Daily Papers
- Published: 2026-10-27T00:00:00.000Z
- RoboHot: https://robohot.news/en/items/osor9xp53nw3xsh2rwcq3haaw
- Original: https://huggingface.co/papers/2509.05512

## Summary

The paper proposes Quaternion Approximate Networks (QUAN), which approximate quaternion convolution through Hamilton product decomposition using real-valued operations, paired with custom CUDA kernels to achieve rotation-equivariant image classification and object detection. The authors also propose Independent Quaternion Batch Normalization (IQBN) to stabilize training and extend quaternion operations to spatial attention mechanisms.