Wavelet Convolutional Neural Networks

Abstract

Spatial and spectral approaches are two major approaches for image processing tasks such as image classification and object recognition. Among many such algorithms, convolutional neural networks (CNNs) have recently achieved significant performance improvement in many challenging tasks. Since CNNs process images directly in the spatial domain, they are essentially spatial approaches. Given that spatial and spectral approaches are known to have different characteristics, it will be interesting to incorporate a spectral approach into CNNs. We propose a novel CNN architecture, wavelet CNNs, which combines a multiresolution analysis and CNNs into one model. Our insight is that a CNN can be viewed as a limited form of a multiresolution analysis. Based on this insight, we supplement missing parts of the multiresolution analysis via wavelet transform and integrate them as additional components in the entire architecture. Wavelet CNNs allow us to utilize spectral information which is mostly lost in conventional CNNs but useful in most image processing tasks. We evaluate the practical performance of wavelet CNNs on texture classification and image annotation. The experiments show that wavelet CNNs can achieve better accuracy in both tasks than existing models while having significantly fewer parameters than conventional CNNs.

arXiv comment10 pages, 7 figures, 5 tables. arXiv admin note: substantial text overlap with arXiv:1707.07394

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Residual Learning for Image Recognition
• Striving for Simplicity: The All Convolutional Net
• Wide Residual Networks
• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• Residual Networks of Residual Networks: Multilevel Residual Networks
• Compact Bilinear Pooling
• Annotation Order Matters: Recurrent Image Annotator for Arbitrary Length Image Tagging

Cited by in corpus (10)

• Joint Time-Frequency Scattering
• WaveMamba: Spatial-Spectral Wavelet Mamba for Hyperspectral Image Classification
• SpectralNET: Exploring Spatial-Spectral WaveletCNN for Hyperspectral Image Classification
• WaveletAE: A Wavelet-enhanced Autoencoder for Wind Turbine Blade Icing Detection
• Deep Learning for Multi-Scale Changepoint Detection in Multivariate Time Series
• Translating Diffusion, Wavelets, and Regularisation into Residual Networks
• Self-Supervised Learning of a Biologically-Inspired Visual Texture Model
• Learnable Gabor modulated complex-valued networks for orientation robustness
• WaDeNet: Wavelet Decomposition based CNN for Speech Processing
• Deep Adaptive Wavelet Network