Scaling Laws For Deep Learning Based Image Reconstruction

Tobit Klug, Reinhard Heckel

Keywords: scaling laws, number of training examples, inverse problems, deep learning, denoising, magnetic resonance imaging, super-resolution

TL;DR: The performance improvement of deep learning based image reconstruction methods as a function of the training set size slows already at moderate training set sizes, indicating that only marginal gains are expected beyond a few thousand examples.

Abstract:

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.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2209.13435/code)