WaveSNet: Wavelet Integrated Deep Networks for Image Segmentation

Li, Qiufu; Shen, Linlin

doi:10.48550/arxiv.2005.14461

Cited by 5 publications

(9 citation statements)

References 10 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wavelet decomposition is well known and widely used in signal processing, but its usage in the computer vision community is limited. Works, such as [30], [31], [32] embed wavelets into the neural network to do 2D classification, image segmentation, and image restoration. Fujieda and Takayama [30] presented a multi-resolution analysis and CNNs combination for texture classification and image annotation.…”

Section: D Object Detection Using Lidar Point Cloudsmentioning

confidence: 99%

“…The authors achieved significant performance improvement over the CNN models with fewer parameters. Shen proposed WaveSNet [31] a wavelet integrated deep network for image segmentation applications. The author integrated discrete wavelet transform into U-Net [33], SegNet [34], and DeepLabv3+ [35] models for effective image segmentation.…”

Section: D Object Detection Using Lidar Point Cloudsmentioning

confidence: 99%

See 1 more Smart Citation

WCNN3D: Wavelet Convolutional Neural Network Based 3D Object Detection for Autonomous Driving

Alaba¹,

Ball²

2022

Preprint

View full text Add to dashboard Cite

3D object detection is crucial for autonomous driving to understand the driving environment. Since the pooling operation causes information loss in the standard CNN, we have designed a wavelet multiresolution analysis-based 3D object detection network without a pooling operation. Additionally, instead of using a single filter like the standard convolution, we use the lower-frequency and higher-frequency coefficients as a filter. These filters capture more relevant parts than a single filter, enlarging the receptive field. The model comprises a discrete wavelet transform (DWT) and an inverse wavelet transform (IWT) with skip connections to encourage feature reuse for contrasting and expanding layers. The IWT enriches the feature representation by fully recovering the lost details during the downsampling operation. Element-wise summation is used for the skip connections to decrease the computational burden. We train the model for the Haar and Daubechies (Db4) wavelets. The two-level wavelet decomposition result shows that we can build a lightweight model without losing significant performance. The experimental results on the KITTI’s BEV and 3D evaluation benchmark show our model outperforms the Pointpillars base model by up to 14 \% while reducing the number of trainable parameters. Code will be released.

show abstract

Section: D Object Detection Using Lidar Point Cloudsmentioning

confidence: 99%

Section: D Object Detection Using Lidar Point Cloudsmentioning

confidence: 99%

WCNN3D: Wavelet Convolutional Neural Network Based 3D Object Detection for Autonomous Driving

Alaba¹,

Ball²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In comparison, our WaveCNets are justified by the well defined wavelet theory [10], [11]. Both the usual down-sampling and up-sampling operations can be replaced by DWT and IDWT [17], [28], respectively.…”

Section: B Down-samplingmentioning

confidence: 99%

“…However, these up-sampling operations can not precisely recover the original data, due to the absence of the strict mathematical terms. They do not perform well in the restoration of image details, while the proposed DWT/IDWT layer could relieve this drawback [28].…”

Section: B Down-samplingmentioning

confidence: 99%

WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification

Shen

Guo³

et al. 2021

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

Though widely used in image classification, convolutional neural networks (CNNs) are prone to noise interruptions, i.e. the CNN output can be drastically changed by small image noise. To improve the noise robustness, we try to integrate CNNs with wavelet by replacing the common down-sampling (maxpooling, strided-convolution, and average pooling) with discrete wavelet transform (DWT). We firstly propose general DWT and inverse DWT (IDWT) layers applicable to various orthogonal and biorthogonal discrete wavelets like Haar, Daubechies, and Cohen, etc., and then design wavelet integrated CNNs (WaveCNets) by integrating DWT into the commonly used CNNs (VGG, ResNets, and DenseNet). During the down-sampling, WaveCNets apply DWT to decompose the feature maps into the low-frequency and high-frequency components. Containing the main information including the basic object structures, the low-frequency component is transmitted into the following layers to generate robust high-level features. The high-frequency components are dropped to remove most of the data noises. The experimental results show that WaveCNets achieve higher accuracy on ImageNet than various vanilla CNNs. We have also tested the performance of WaveCNets on the noisy version of ImageNet, ImageNet-C and six adversarial attacks, the results suggest that the proposed DWT/IDWT layers could provide better noise-robustness and adversarial robustness. When applying WaveCNets as backbones, the performance of object detectors (i.e., faster R-CNN and RetinaNet) on COCO detection dataset are consistently improved. We believe that suppression of aliasing effect, i.e. separation of low frequency and high frequency information, is the main advantages of our approach. The code of our DWT/IDWT layer and different WaveCNets are available at https://github.com/CVI-SZU/WaveCNet.

show abstract

“…In image processing, wavelet transform is often used as a tool for content information analysis [34]. With the development of DNNs, wavelet transform has several attempts to combine the classical signal processing and deep learning methods, such as image denoising [20,31,47], super resolution [16,30], classification [7,25,29], segmentation [24], facial aging [32], style transfer [50], remote sensing image processing [9], etc. It is often used as the tool of data preprocessing, post-processing, feature extraction, and sampling operators in DNNs [16,32,39,48,30,23].…”

Section: Waveletsmentioning

confidence: 99%

MWQ: Multiscale Wavelet Quantized Neural Networks

Sun¹,

Ren²,

Jiao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Model quantization can reduce the model size and computational latency, it has become an essential technique for the deployment of deep neural networks on resourceconstrained hardware (e.g., mobile phones and embedded devices). The existing quantization methods mainly consider the numerical elements of the weights and activation values, ignoring the relationship between elements. The decline of representation ability and information loss usually lead to the performance degradation. Inspired by the characteristics of images in the frequency domain, we propose a novel multiscale wavelet quantization (MWQ) method. This method decomposes original data into multiscale frequency components by wavelet transform, and then quantizes the components of different scales, respectively. It exploits the multiscale frequency and spatial information to alleviate the information loss caused by quantization in the spatial domain. Because of the flexibility of MWQ, we demonstrate three applications (e.g., model compression, quantized network optimization, and information enhancement) on the ImageNet and COCO datasets. Experimental results show that our method has stronger representation ability and can play an effective role in quantized neural networks.

show abstract

WaveSNet: Wavelet Integrated Deep Networks for Image Segmentation

Cited by 5 publications

References 10 publications

WCNN3D: Wavelet Convolutional Neural Network Based 3D Object Detection for Autonomous Driving

WCNN3D: Wavelet Convolutional Neural Network Based 3D Object Detection for Autonomous Driving

WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification

MWQ: Multiscale Wavelet Quantized Neural Networks

Contact Info

Product

Resources

About