dAUTOMAP: decomposing AUTOMAP to achieve scalability and enhance performance

09/24/2019
by   Jo Schlemper, et al.
30

AUTOMAP is a promising generalized reconstruction approach, however, it is not scalable and hence the practicality is limited. We present dAUTOMAP, a novel way for decomposing the domain transformation of AUTOMAP, making the model scale linearly. We show dAUTOMAP outperforms AUTOMAP with significantly fewer parameters.

READ FULL TEXT
research
08/16/2019

ScarletNAS: Bridging the Gap Between Scalability and Fairness in Neural Architecture Search

One-shot neural architecture search features fast training of a supernet...
research
02/04/2022

Image-to-Image MLP-mixer for Image Reconstruction

Neural networks are highly effective tools for image reconstruction prob...
research
03/02/2023

Semiparametric Language Models Are Scalable Continual Learners

Semiparametric language models (LMs) have shown promise in continuously ...
research
01/20/2021

Scalable Deep Compressive Sensing

Deep learning has been used to image compressive sensing (CS) for enhanc...
research
07/05/2017

Robust Multi-Image HDR Reconstruction for the Modulo Camera

Photographing scenes with high dynamic range (HDR) poses great challenge...
research
07/08/2019

Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching

A broad range of cross-m-domain generation researches boil down to match...
research
11/07/2018

Interpreting the Ising Model: The Input Matters

The Ising model is a widely used model for multivariate binary data. It ...

Please sign up or login with your details

Forgot password? Click here to reset