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 2209.13435eess.IVcs.AIcs.CVcs.LGstat.ML
收藏

基于深度学习的图像重建的尺度律

Scaling Laws For Deep Learning Based Image Reconstruction

Technical University of Munich(慕尼黑工业大学)

Tobit Klug, Reinhard Heckel

摘要:

经过端到端训练的深度神经网络将(噪声)图像的测量映射到干净的图像,对于各种线性逆问题表现出色。目前的方法只在几百或几千张图像上训练,而在其他领域,深度网络训练了数百万个例子。在这项工作中,我们研究是否主要的性能增益预计从扩大训练集的大小。我们考虑图像去噪、加速磁共振成像和超分辨率,并根据经验确定重建质量作为训练集大小的函数,同时缩放网络大小。对于所有三个任务,我们发现,一个最初陡峭的幂律缩放显着放缓已经在中等规模的训练集。插值这些缩放定律表明,即使在数百万张图像上进行训练也不会显着提高性能。为了理解预期的行为,我们分析了用早期停止的梯度下降学习的线性估计器的性能。该结果形式化了这样的直觉,即一旦通过学习信号模型引起的误差相对于误差下限较小,则更多的训练示例不会提高性能。

英文摘要:

Deep neural networks trained end-to-end to map a measurement of a (noisy) image to a clean image perform excellent for a variety of linear inverse problems. Current methods are only trained on a few hundreds or thousands of images as opposed to the millions of examples deep networks are trained on in other domains. In this work, we study whether major performance gains are expected from scaling up the training set size. We consider image denoising, accelerated magnetic resonance imaging, and super-resolution and empirically determine the reconstruction quality as a function of training set size, while simultaneously scaling the network size. For all three tasks we find that an initially steep power-law scaling slows significantly already at moderate training set sizes. Interpolating those scaling laws suggests that even training on millions of images would not significantly improve performance. To understand the expected behavior, we analytically characterize the performance of a linear estimator learned with early stopped gradient descent. The result formalizes the intuition that once the error induced by learning the signal model is small relative to the error floor, more training examples do not improve performance.

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。

↑