Texture classification is one of the essential problems in computer vision. Due to the powerful feature extraction ability, convolutional neural network (CNN) based texture classification methods have attracted extensive attention in recent years. However, there are still some challenges, such as the extraction of multi-level texture features and their relationships. To address these problems, this letter proposes the wavelet multi-level attention capsule network (WMACapsNet), which integrates multi-scale wavelet decomposition and multi-level attention blocks into the capsule network. Specifically, multi-scale spectral features in frequency domain are extracted by multi-level wavelet transform; and then the self-attention block explores the dependencies of capsule features within each scale; finally, the cross-attention block refines capsule features and their relationships with attention mechanism across different scales. The proposed WMACapsNet provides an efficient way to explore spatial domain features, frequency domain features and their dependencies, useful for most texture classification tasks. Experimental results on several texture datasets show that the proposed WMACapsNet outperforms the state-of-the-art texture classification methods not only in accuracy but also in robustness.

中文翻译：

---

用于纹理分类的小波多级注意力胶囊网络


纹理分类是计算机视觉中的基本问题之一。由于强大的特征提取能力，基于卷积神经网络（CNN）的纹理分类方法近年来引起了广泛的关注。然而，仍然存在一些挑战，例如多级纹理特征及其关系的提取。为了解决这些问题，这封信提出了小波多级注意力胶囊网络（WMACapsNet），它将多尺度小波分解和多级注意力块集成到胶囊网络中。具体地，通过多级小波变换提取频域多尺度频谱特征；然后自注意力模块探索每个尺度内胶囊特征的依赖性；最后，交叉注意力模块细化了不同尺度的胶囊特征及其与注意力机制的关系。所提出的 WMACapsNet 提供了一种有效的方法来探索空间域特征、频域特征及其依赖性，对于大多数纹理分类任务很有用。在多个纹理数据集上的实验结果表明，所提出的 WMACapsNet 不仅在准确性上而且在鲁棒性上都优于最先进的纹理分类方法。