paper-with-me

홈 › Papers

Multiplierless Modules for Forward and Backward Integer Wavelet Transform

2010-10-19 · Vasil Kolev

This article is about the architecture of a lossless wavelet filter bank with reprogrammable logic. It is based on second generation of wavelets with a reduced of number of operations. A new basic structure for parallel architecture and modules to forward and backward integer discrete wavelet transform is proposed.

📄 PDF Abstract BibTeX arXiv:1010.4059

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation

2022-09-20 · Mohammadreza Tayaranian, Alireza Ghaffari, Marzieh S. Tahaei, Mehdi Rezagholizadeh 외

The large number of parameters of some prominent language models, such as BERT, makes their fine-tuning on downstream tasks computationally intensive and energy hungry. Previously researchers were focused on lower bit-wi…

Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One

2023-04-20 · Hongyuan Zhang, Yanan Zhu, Xuelong Li

Graph neural networks (GNN) suffer from severe inefficiency. It is mainly caused by the exponential growth of node dependency with the increase of layers. It extremely limits the application of stochastic optimization al…

Stochastic Optimization

Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-ahead Forward Ones

2022-04-12 · Junyi Li, Xiaohe Wu, Zhenxing Niu, WangMeng Zuo

While significant progress has been made in deep video denoising, it remains very challenging for exploiting historical and future frames. Bidirectional recurrent networks (BiRNN) have exhibited appealing performance in …

DenoisingVideo DenoisingVideo Restoration

WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability

2022-10-05 · Yufan Zhuang, Zihan Wang, Fangbo Tao, Jingbo Shang

Transformer and its variants are fundamental neural architectures in deep learning. Recent works show that learning attention in the Fourier space can improve the long sequence learning capability of Transformers. We arg…

Wavelet Domain Residual Network (WavResNet) for Low-Dose X-ray CT Reconstruction

2017-03-04 · Eunhee Kang, Junhong Min, Jong Chul Ye

Model based iterative reconstruction (MBIR) algorithms for low-dose X-ray CT are computationally complex because of the repeated use of the forward and backward projection. Inspired by this success of deep learning in co…

CT ReconstructionLow-Dose X-Ray Ct Reconstruction