arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.12728eess.SPcs.CVeess.IV
收藏

ATP-Net:一种基于注意力的三值投影压缩感知网络

ATP-Net: An Attention-based Ternary Projection Network For Compressed Sensing

Beijing University of Posts and Telecommunications(北京邮电大学)

Guanxiong Nie, Yajian Zhou

摘要:

压缩感知(CS)理论同时实现了信号的采样和压缩过程,可以用更少的观测值实现精确的信号恢复,为海量数据更好更快的传输提供了解决方案。针对CS采样矩阵多为随机矩阵,与采样信号无关且存储空间大的问题,提出了一种基于三值采样矩阵的带注意机制的CS采样方法。所提出的方法包括三个部分,即,三值采样、初始重构和深度重构,重点是三值采样。三值化方法(-1,0,+1)的主要思想是在对采样矩阵进行二值化(-1,+1)后,在采样层引入注意力机制来评估参数的重要性,然后对重要性低于预定义阈值的参数进行修剪权重,从而实现三值化。在此基础上,提出了一种基于三值采样矩阵的压缩感知算法,即ATP-Net,用于图像重建,基于注意力的三元投影网络。实验结果表明,采用三值采样矩阵,即,在采样率为0.25时,Set 11的平均PSNR为30.4,比DR 2-Net提高了约6%。

英文摘要:

Compressed Sensing (CS) theory simultaneously realizes the signal sampling and compression process, and can use fewer observations to achieve accurate signal recovery, providing a solution for better and faster transmission of massive data. In this paper, a ternary sampling matrix-based method with attention mechanism is proposed with the purpose to solve the problem that the CS sampling matrices in most cases are random matrices, which are irrelative to the sampled signal and need a large storage space. The proposed method consists of three components, i.e., ternary sampling, initial reconstruction and deep reconstruction, with the emphasis on the ternary sampling. The main idea of the ternary method (-1, 0, +1) is to introduce the attention mechanism to evaluate the importance of parameters at the sampling layer after the sampling matrix is binarized (-1, +1), followed by pruning weight of parameters, whose importance is below a predefined threshold, to achieve ternarization. Furthermore, a compressed sensing algorithm especially for image reconstruction is implemented, on the basis of the ternary sampling matrix, which is called ATP-Net, i.e., Attention-based ternary projection network. Experimental results show that the quality of image reconstruction by means of ATP-Net maintains a satisfactory level with the employment of the ternary sampling matrix, i.e., the average PSNR on Set11 is 30.4 when the sampling rate is 0.25, approximately 6% improvement compared with that of DR2-Net.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑