# Wavelet Convolutional Neural Networks for Texture Classification

arXiv: https://arxiv.org/abs/1707.07394 · HTML: https://mlsanity.com/paper/1707.07394/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2017.

## Built on by (most cited first, 21 of 21)

- [Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation](https://mlsanity.com/paper/2203.06321/) (2022)
- [FreeKD: Knowledge Distillation via Semantic Frequency Prompt](https://mlsanity.com/paper/2311.12079/) (2023)
- [MaPa: Text-driven Photorealistic Material Painting for 3D Shapes](https://mlsanity.com/paper/2404.17569/) (2024)
- [Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2203.07656/) (2022)
- [SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification](https://mlsanity.com/paper/2104.00341/) (2021)
- [Continual Learning in the Frequency Domain](https://mlsanity.com/paper/2410.06645/) (2024)
- [MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis](https://mlsanity.com/paper/2104.04767/) (2021)
- [Can we integrate spatial verification methods into neural-network loss functions for atmospheric science?](https://mlsanity.com/paper/2203.11141/) (2022)
- [A Novel Bio-Inspired Texture Descriptor based on Biodiversity and Taxonomic Measures](https://mlsanity.com/paper/2102.06997/) (2021)
- [On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks](https://mlsanity.com/paper/2209.11740/) (2022)
- [Computational Modeling of Deep Multiresolution-Fractal Texture and Its Application to Abnormal Brain Tissue Segmentation](https://mlsanity.com/paper/2306.04754/) (2023)
- [DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision](https://mlsanity.com/paper/2309.06941/) (2023)
- [Texture Classification Network Integrating Adaptive Wavelet Transform](https://mlsanity.com/paper/2404.05300/) (2024)
- [Guided Self-attention: Find the Generalized Necessarily Distinct Vectors for Grain Size Grading](https://mlsanity.com/paper/2410.05762/) (2024)
- [Multiscale Analysis for Improving Texture Classification](https://mlsanity.com/paper/2204.09841/) (2022)
- [Texture Extraction Methods Based Ensembling Framework for Improved Classification](https://mlsanity.com/paper/2206.04158/) (2022)
- [VisTaNet: Attention Guided Deep Fusion for Surface Roughness Classification](https://mlsanity.com/paper/2209.08516/) (2022)
- [GraphTEN: Graph Enhanced Texture Encoding Network](https://mlsanity.com/paper/2503.13991/) (2025)
- [Freqformer: Image-Demoir'eing Transformer via Effective Frequency Decomposition](https://mlsanity.com/paper/2505.19120/) (2025)
- [SpectraFlow: Unifying Structural Pretraining and Frequency Adaptation for Medical Image Segmentation](https://mlsanity.com/paper/2605.14566/) (2026)
- [Texture Image Classification Using DWT AlexNet Feature Fusion and Deep Neural Networks](https://mlsanity.com/paper/2608.28524/) (2026)

## Abstract (arXiv)

Texture classification is an important and challenging problem in many image processing applications. While convolutional neural networks (CNNs) achieved significant successes for image classification, texture classification remains a difficult problem since textures usually do not contain enough information regarding the shape of object. In image processing, texture classification has been traditionally studied well with spectral analyses which exploit repeated structures in many textures. Since CNNs process images as-is in the spatial domain whereas spectral analyses process images in the frequency domain, these models have different characteristics in terms of performance. We propose a novel CNN architecture, wavelet CNNs, which integrates a spectral analysis into CNNs. Our insight is that the pooling layer and the convolution layer can be viewed as a limited form of a spectral analysis. Based on this insight, we generalize both layers to perform a spectral analysis with wavelet transform. Wavelet CNNs allow us to utilize spectral information which is lost in conventional CNNs but useful in texture classification. The experiments demonstrate that our model achieves better accuracy in texture classification than existing models. We also show that our model has significantly fewer parameters than CNNs, making our model easier to train with less memory.