arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.19134cs.CV
收藏

映射网络

Mapping Networks

National Institute of Technology Rourkela Odisha(印度奥迪沙省拉尔克ela国家理工学院)

Lord Sen, Shyamapada Mukherjee

AI总结:

映射网络通过降低参数数量显著减少过拟合,实现复杂视觉任务中与目标网络相当或更好的性能。

摘要:

现代深度学习模型中参数数量的持续增长对高效训练和解决过拟合问题构成了根本性的挑战。我们通过引入映射网络来应对这一问题,该网络用一个紧凑且可训练的潜在向量替代高维权重空间,基于假设大型网络的训练参数位于平滑的低维流形上。由此,通过专门的映射损失强制执行的映射定理,展示了从潜在空间到目标权重空间的映射在理论和实践中都存在。映射网络显著减少了过拟合,并在复杂的视觉和序列任务中,如图像分类、深度伪造检测等,实现了与目标网络相当或更好的性能,可将可训练参数数量减少至原来的99.5%,即约500倍。

英文摘要:

The escalating parameter counts in modern deep learning models pose a fundamental challenge to efficient training and resolution of overfitting. We address this by introducing the \emph{Mapping Networks} which replace the high dimensional weight space by a compact, trainable latent vector based on the hypothesis that the trained parameters of large networks reside on smooth, low-dimensional manifolds. Henceforth, the Mapping Theorem enforced by a dedicated Mapping Loss, shows the existence of a mapping from this latent space to the target weight space both theoretically and in practice. Mapping Networks significantly reduce overfitting and achieve comparable to better performance than target network across complex vision and sequence tasks, including Image Classification, Deepfake Detection etc, with $\mathbf{99.5\%}$, i.e., around $500\times$ reduction in trainable parameters.

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。

↑