DeepAI AI Chat
Log In Sign Up

One-dimensional Deep Image Prior for Time Series Inverse Problems

by   Sriram Ravula, et al.
The University of Texas at Austin

We extend the Deep Image Prior (DIP) framework to one-dimensional signals. DIP is using a randomly initialized convolutional neural network (CNN) to solve linear inverse problems by optimizing over weights to fit the observed measurements. Our main finding is that properly tuned one-dimensional convolutional architectures provide an excellent Deep Image Prior for various types of temporal signals including audio, biological signals, and sensor measurements. We show that our network can be used in a variety of recovery tasks including missing value imputation, blind denoising, and compressed sensing from random Gaussian projections. The key challenge is how to avoid overfitting by carefully tuning early stopping, total variation, and weight decay regularization. Our method requires up to 4 times fewer measurements than Lasso and outperforms NLM-VAMP for random Gaussian measurements on audio signals, has similar imputation performance to a Kalman state-space model on a variety of data, and outperforms wavelet filtering in removing additive noise from air-quality sensor readings.


page 1

page 2

page 3

page 4


Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation

Un-trained convolutional neural networks have emerged as highly successf...

Compressed Sensing with Invertible Generative Models and Dependent Noise

We study image inverse problems with invertible generative priors, speci...

Regularizing linear inverse problems with convolutional neural networks

Deep convolutional neural networks trained on large datsets have emerged...

Compressed Sensing with Deep Image Prior and Learned Regularization

We propose a novel method for compressed sensing recovery using untraine...

Solving Inverse Problems with Hybrid Deep Image Priors: the challenge of preventing overfitting

We mainly analyze and solve the overfitting problem of deep image prior ...

Solving Inverse Problems With Deep Neural Networks – Robustness Included?

In the past five years, deep learning methods have become state-of-the-a...

Rethinking Deep Image Prior for Denoising

Deep image prior (DIP) serves as a good inductive bias for diverse inver...