MIXER: Mixed Hyperspherical Random Embedding Neural Network for Texture Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916987467202560 |
|---|---|
| author | Fares, Ricardo T. Ribas, Lucas C. |
| author_facet | Fares, Ricardo T. Ribas, Lucas C. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_03228 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MIXER: Mixed Hyperspherical Random Embedding Neural Network for Texture Recognition Fares, Ricardo T. Ribas, Lucas C. Computer Vision and Pattern Recognition 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. |
| title | MIXER: Mixed Hyperspherical Random Embedding Neural Network for Texture Recognition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.03228 |