# MIXER: Mixed Hyperspherical Random Embedding Neural Network for Texture Recognition

arXiv: https://arxiv.org/abs/2510.03228 · HTML: https://mlsanity.com/paper/2510.03228/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 51 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks](https://mlsanity.com/paper/2112.01715/) (2021)
- [Deep TEN: Texture Encoding Network](https://mlsanity.com/paper/1612.02844/) (2016)
- [From BoW to CNN: Two Decades of Texture Representation for Texture Classification](https://mlsanity.com/paper/1801.10324/) (2018)
- [Deep Texture Manifold for Ground Terrain Recognition](https://mlsanity.com/paper/1803.10896/) (2018)
- [Lightweight Pixel Difference Networks for Efficient Visual Representation Learning](https://mlsanity.com/paper/2402.00422/) (2024)
- [RADAM: Texture Recognition through Randomized Aggregated Encoding of Deep Activation Maps](https://mlsanity.com/paper/2303.04554/) (2023)
- [Fusion of complex networks and randomized neural networks for texture analysis](https://mlsanity.com/paper/1806.09170/) (2018)
- [Spatio-spectral networks for color-texture analysis](https://mlsanity.com/paper/1909.06446/) (2019)
- [Hyperspherical Embedding for Point Cloud Completion](https://mlsanity.com/paper/2307.05634/) (2023)
- [Multilayer Complex Network Descriptors for Color-Texture Characterization](https://mlsanity.com/paper/1804.00501/) (2018)

## Abstract (arXiv)

Randomized neural networks for representation learning have consistently achieved prominent results in texture recognition tasks, effectively combining the advantages of both traditional techniques and learning-based approaches. However, existing approaches have so far focused mainly on improving cross-information prediction, without introducing significant advancements to the overall randomized network architecture. In this paper, we propose Mixer, a novel randomized neural network for texture representation learning. At its core, the method leverages hyperspherical random embeddings coupled with a dual-branch learning module to capture both intra- and inter-channel relationships, further enhanced by a newly formulated optimization problem for building rich texture representations. Experimental results have shown the interesting results of the proposed approach across several pure texture benchmarks, each with distinct characteristics and challenges. The source code will be available upon publication.