BriefGPT.xyz
May, 2023
自监督图像重建方法的样本复杂度分析
Analyzing the Sample Complexity of Self-Supervised Image Reconstruction Methods
HTML
PDF
Tobit Klug, Dogukan Atik, Reinhard Heckel
TL;DR
探究自监督训练方法的样本复杂度,发现模型的性能会随着训练样本数量增加而提高,证明采用自监督训练方法所需样本较多,但与监督训练方法优化模型的性能差距会随着样本数量增加而逐渐缩小。
Abstract
supervised training
of deep
neural networks
on pairs of clean image and noisy measurement achieves state-of-the-art performance for many
image re
→