Auto Machine Learning for Medical Image Analysis by Unifying the Search on Data Augmentation and Neural Architecture

07/21/2022
by   Jianwei Zhang, et al.
19

Automated data augmentation, which aims at engineering augmentation policy automatically, recently draw a growing research interest. Many previous auto-augmentation methods utilized a Density Matching strategy by evaluating policies in terms of the test-time augmentation performance. In this paper, we theoretically and empirically demonstrated the inconsistency between the train and validation set of small-scale medical image datasets, referred to as in-domain sampling bias. Next, we demonstrated that the in-domain sampling bias might cause the inefficiency of Density Matching. To address the problem, an improved augmentation search strategy, named Augmented Density Matching, was proposed by randomly sampling policies from a prior distribution for training. Moreover, an efficient automatical machine learning(AutoML) algorithm was proposed by unifying the search on data augmentation and neural architecture. Experimental results indicated that the proposed methods outperformed state-of-the-art approaches on MedMNIST, a pioneering benchmark designed for AutoML in medical image analysis.

READ FULL TEXT

page 1

page 6

research
09/30/2021

DAAS: Differentiable Architecture and Augmentation Policy Search

Neural architecture search (NAS) has been an active direction of automat...
research
03/14/2021

Principled Ultrasound Data Augmentation for Classification of Standard Planes

Deep learning models with large learning capacities often overfit to med...
research
03/30/2021

Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial Training

Data augmentation has proved extremely useful by increasing training dat...
research
05/09/2020

AutoCLINT: The Winning Method in AutoCV Challenge 2019

NeurIPS 2019 AutoDL challenge is a series of six automated machine learn...
research
02/21/2020

Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation

Test-time data augmentation—averaging the predictions of a machine learn...
research
02/02/2023

Neural Network Architecture for Database Augmentation Using Shared Features

The popularity of learning from data with machine learning and neural ne...
research
07/12/2018

Hydranet: Data Augmentation for Regression Neural Networks

Despite recent efforts, deep learning techniques remain often heavily de...

Please sign up or login with your details

Forgot password? Click here to reset