WaveSNet: Wavelet Integrated Deep Networks for Image Segmentation
This addresses the issue of detail loss in image segmentation for computer vision applications, but it is incremental as it builds on existing architectures like U-Net, SegNet, and DeepLabv3+.
The paper tackles the problem of lost data details degrading image segmentation performance in deep networks by integrating Discrete Wavelet Transform (DWT) and Inverse DWT (IDWT) as network layers to extract and recover details during down-sampling and up-sampling, resulting in improved segmentation performances on datasets like CamVid, Pascal VOC, and Cityscapes compared to vanilla versions.
In deep networks, the lost data details significantly degrade the performances of image segmentation. In this paper, we propose to apply Discrete Wavelet Transform (DWT) to extract the data details during feature map down-sampling, and adopt Inverse DWT (IDWT) with the extracted details during the up-sampling to recover the details. We firstly transform DWT/IDWT as general network layers, which are applicable to 1D/2D/3D data and various wavelets like Haar, Cohen, and Daubechies, etc. Then, we design wavelet integrated deep networks for image segmentation (WaveSNets) based on various architectures, including U-Net, SegNet, and DeepLabv3+. Due to the effectiveness of the DWT/IDWT in processing data details, experimental results on CamVid, Pascal VOC, and Cityscapes show that our WaveSNets achieve better segmentation performances than their vanilla versions.