MIXER: Mixed Hyperspherical Random Embedding Neural Network for Texture Recognition
This work addresses texture recognition for computer vision applications, but it appears incremental as it builds on existing randomized network approaches without clear broad impact.
The paper tackled texture recognition by proposing MIXER, a randomized neural network that uses hyperspherical random embeddings and a dual-branch module to capture intra- and inter-channel relationships, achieving interesting results on multiple texture benchmarks.
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.