# Wavelet Integrated CNNs for Noise-Robust Image Classification

arXiv: https://arxiv.org/abs/2005.03337 · HTML: https://mlsanity.com/paper/2005.03337/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2020.

## Built on by (most cited first, 30 of 60)

- [Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection](https://mlsanity.com/paper/2312.16649/) (2023)
- [Wavelet Diffusion Models are fast and scalable Image Generators](https://mlsanity.com/paper/2211.16152/) (2022)
- [Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity](https://mlsanity.com/paper/2203.05151/) (2022)
- [WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis](https://mlsanity.com/paper/2402.19043/) (2024)
- [A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?](https://mlsanity.com/paper/2112.00639/) (2021)
- [Single Image Depth Prediction with Wavelet Decomposition](https://mlsanity.com/paper/2106.02022/) (2021)
- [WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification](https://mlsanity.com/paper/2107.13335/) (2021)
- [Wavelet Diffusion Neural Operator](https://mlsanity.com/paper/2412.04833/) (2024)
- [FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting](https://mlsanity.com/paper/2204.00491/) (2022)
- [WaveMix: A Resource-efficient Neural Network for Image Analysis](https://mlsanity.com/paper/2205.14375/) (2022)
- [Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulation](https://mlsanity.com/paper/2309.09667/) (2023)
- [HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models](https://mlsanity.com/paper/2404.04876/) (2024)
- [HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness](https://mlsanity.com/paper/2307.11823/) (2023)
- [Continual Learning in the Frequency Domain](https://mlsanity.com/paper/2410.06645/) (2024)
- [Group-wise Inhibition based Feature Regularization for Robust Classification](https://mlsanity.com/paper/2103.02152/) (2021)
- [Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function](https://mlsanity.com/paper/2110.00899/) (2021)
- [Wavelet-Based Network For High Dynamic Range Imaging](https://mlsanity.com/paper/2108.01434/) (2021)
- [WaveMix: Resource-efficient Token Mixing for Images](https://mlsanity.com/paper/2203.03689/) (2022)
- [Activation Space Selectable Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2408.08338/) (2024)
- [Wavelet-Attention CNN for Image Classification](https://mlsanity.com/paper/2201.09271/) (2022)
- [WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks](https://mlsanity.com/paper/2310.11595/) (2023)
- [M2SFormer: Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localization](https://mlsanity.com/paper/2506.20922/) (2025)
- [Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition](https://mlsanity.com/paper/2402.02210/) (2024)
- [Streaming Drag-Oriented Interactive Video Manipulation: Drag Anything, Anytime!](https://mlsanity.com/paper/2510.03550/) (2025)
- [MWQ: Multiscale Wavelet Quantized Neural Networks](https://mlsanity.com/paper/2103.05363/) (2021)
- [BVINet: Unlocking Blind Video Inpainting with Zero Annotations](https://mlsanity.com/paper/2502.01181/) (2025)
- [One Model for All Quantization: A Quantized Network Supporting Hot-Swap Bit-Width Adjustment](https://mlsanity.com/paper/2105.01353/) (2021)
- [Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks](https://mlsanity.com/paper/2106.00673/) (2021)
- [Can we integrate spatial verification methods into neural-network loss functions for atmospheric science?](https://mlsanity.com/paper/2203.11141/) (2022)
- [Preservation of High Frequency Content for Deep Learning-Based Medical Image Classification](https://mlsanity.com/paper/2205.03898/) (2022)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) are generally prone to noise interruptions, i.e., small image noise can cause drastic changes in the output. To suppress the noise effect to the final predication, we enhance CNNs by replacing max-pooling, strided-convolution, and average-pooling with Discrete Wavelet Transform (DWT). We present general DWT and Inverse DWT (IDWT) layers applicable to various wavelets like Haar, Daubechies, and Cohen, etc., and design wavelet integrated CNNs (WaveCNets) using these layers for image classification. In WaveCNets, feature maps are decomposed into the low-frequency and high-frequency components during the down-sampling. The low-frequency component stores main information including the basic object structures, which is transmitted into the subsequent layers to extract robust high-level features. The high-frequency components, containing most of the data noise, are dropped during inference to improve the noise-robustness of the WaveCNets. Our experimental results on ImageNet and ImageNet-C (the noisy version of ImageNet) show that WaveCNets, the wavelet integrated versions of VGG, ResNets, and DenseNet, achieve higher accuracy and better noise-robustness than their vanilla versions.