Wavelet Multi-Level Attention Capsule Network for Texture Classification

Abstract

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.