卷积自编码器的免训练瓶颈宽度规划

中文摘要 AI 辅助

多尺度谱率失真（MS-SRD）方法无需拟合神经网络，即可根据训练图像和归一化均方误差（NMSE）界限，在用户提供的空间切割处估计所需的瓶颈通道数。其协方差尾部规则在平方误差下对共享线性块卷积自编码器是精确的。嵌套尺度优势结果促使在最小潜在候选之外报告激活-参数帕累托前沿。在十三个灰度数据集上，当NMSE≤0.01时，其潜在尺寸预测相对于非线性块自编码器边界的平均绝对百分比误差为0.84%；其中十个预测精确，其余三个相差一个通道。在四个数据集的部署比较中，MS-SRD匹配了所有回顾性外部宽度，且所有四个选定模型均通过，无需训练选择器；一个46次拟合验证网格和四个最小体积拟合均在两个数据集上通过。在相同界限下的跳跃闭合U形自编码器中，五个预测精确，九个在一个通道内，且每个失败预测都少一个通道。在更宽松界限下的实验显示非线性节省逐渐增大。

英文摘要

Multiscale Spectral Rate-Distortion (MS-SRD) estimates the bottleneck channels required at user-supplied spatial cuts from training images and a normalized mean-squared error (NMSE) bound, without fitting a neural network. Its covariance-tail rule is exact for shared linear block-convolutional autoencoders under squared error. A nested-scale dominance result motivates reporting the activation-parameter Pareto frontier alongside the minimum-latent candidate. At NMSE <= 0.01 on thirteen grayscale datasets, its latent-size prediction has 0.84% mean absolute percentage error against nonlinear patch-autoencoder boundaries; ten predictions are exact and the remaining three differ by one channel. In a four-dataset deployable comparison, MS-SRD matches all retrospective external widths and all four selected models pass, without training a selector; a 46-fit validation grid and four Least-Volume fits each pass on two datasets. In a skip-closed U-shaped autoencoder at the same bound, five predictions are exact, nine are within one channel, and every failing prediction is one channel short. Experiments at looser bounds show progressively larger nonlinear savings.

发表机构

• Beihang University（北京航空航天大学）

机构由 AI 辅助整理，请以论文原文为准。