Wavelet Integrated CNNs for Noise-Robust Image Classification

  title={Wavelet Integrated CNNs for Noise-Robust Image Classification},
  author={Qiufu Li and Linlin Shen and Sheng Guo and Zhihui Lai},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Qiufu Li, Linlin Shen, +1 author Zhihui Lai
  • Published 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
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… Expand
Efficient Attention Fusion Network in Wavelet Domain for Demoireing
This paper proposes an efficient attention fusion module (EAFM), a combination of efficient channel attention, spatial attention and local residual learning that can self-adaptively learn various weights of feature information at different levels and inspire the network to focus more on effective information such as moire details to improve learning and demoireing performance. Expand
Wavelet-Based Dual-Branch Network for Image Demoireing
Although designed for image demoireing, WDNet has been applied to two other low-levelvision tasks, outperforming state-of-the-art image deraining and derain-drop methods on the Rain100h and Raindrop800 data sets, respectively. Expand
Group-wise Inhibition based Feature Regularization for Robust Classification
The proposed regularization method is able to achieve a significant gain of robustness over 15% comparing with the state-of-theart and complements other defense paradigms, such as adversarial training, to further improve the robustness. Expand
Receptive Field Size Optimization with Continuous Time Pooling
An altered version of the most commonly applied method, maximum pooling, where pooling in theory is substituted by a continuous time differential equation, which generates a location sensitive pooling operation, more similar to biological receptive fields is presented. Expand
COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data
This study demonstrates how transfer learning from deep learning models can be used to perform COVID-19 detection using images from three most commonly used medical imaging modes X-Ray, Ultrasound, and CT scan to provide over-stressed medical professionals a second pair of eyes through intelligent deep learning image classification models. Expand
Exploring Novel Pooling Strategies for Edge Preserved Feature Maps in Convolutional Neural Networks
With the introduction of anti-aliased convolutional neural networks (CNN), there has been some resurgence in relooking the way pooling is done in CNNs. The fundamental building block of theExpand
3D WaveUNet: 3D Wavelet Integrated Encoder-Decoder Network for Neuron Segmentation
The experimental results show that the neuron segmentation method could completely extract the target neuron in noisy neuronal images and the integrated 3D wavelets can efficiently improve the performance of 3D neurons segmentation and reconstruction. Expand
WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification
  • Qiufu Li, Linlin Shen, Sheng Guo, Zhihui Lai
  • Computer Science, Medicine
  • IEEE Transactions on Image Processing
  • 2021
The proposed DWT/IDWT layers could provide better noise-robustness and adversarial robustness and suppression of aliasing effect, i.e. separation of low frequency and high frequency information, is the main advantages of this approach. Expand
Anti-aliasing Deep Image Classifiers using Novel Depth Adaptive Blurring and Activation Function
This work analyzes deep features with Fourier transform and shows that Depth Adaptive Blurring is more effective, as opposed to monotonic blurring, and outlines how this can replace existing down-sampling methods. Expand


Multi-level Wavelet-CNN for Image Restoration
This paper presents a novel multi-level wavelet CNN model for better tradeoff between receptive field size and computational efficiency, and shows the effectiveness of MWCNN for image denoising, single image super-resolution, and JPEG image artifacts removal. Expand
Wavelet-SRNet: A Wavelet-Based CNN for Multi-scale Face Super Resolution
A wavelet-based CNN approach that can ultra-resolve a very low resolution face image of 16 × 16 or smaller pixelsize to its larger version of multiple scaling factors in a unified framework with three types of loss: wavelet prediction loss, texture loss and full-image loss is presented. Expand
Wavelet Pooling for Convolutional Neural Networks
Making Convolutional Networks Shift-Invariant Again
This work demonstrates that anti-aliasing by low-pass filtering before downsampling, a classical signal processing technique has been undeservingly overlooked in modern deep networks, is compatible with existing architectural components, such as max-pooling and strided-convolution. Expand
Multi-path learnable wavelet neural network for image classification
This paper proposes and evaluates a novel multi-path wavelet neural network architecture for image classification with far less number of trainable parameters and supports the possibility of reducing the number of parameters significantly in deep neural networks without compromising its accuracy. Expand
SAR Image segmentation based on convolutional-wavelet neural network and markov random field
In this approach, a wavelet constrained pooling layer is designed to replace the conventional pooling in CNN and the new architecture can suppress the noise and is better at keeping the structures of the learned features, which are crucial to the segmentation tasks. Expand
ImageNet classification with deep convolutional neural networks
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
Wavelet-enhanced convolutional neural network: a new idea in a deep learning paradigm
Comparing the performance of basic FCN architecture against the wavelet-enhanced form revealed a remarkable superiority of enhanced architecture in brain tumor segmentation tasks. Expand
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures, including FCN and DeconvNet. Expand
Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
A high-performance DNN architecture on ImageNet whose decisions are considerably easier to explain is introduced, and behaves similar to state-of-the art deep neural networks such as VGG-16, ResNet-152 or DenseNet-169 in terms of feature sensitivity, error distribution and interactions between image parts. Expand