DEAL: Deep Evidential Active Learning for Image Classification

07/22/2020
by   Patrick Hemmer, et al.
0

Convolutional Neural Networks (CNNs) have proven to be state-of-the-art models for supervised computer vision tasks, such as image classification. However, large labeled data sets are generally needed for the training and validation of such models. In many domains, unlabeled data is available but labeling is expensive, for instance when specific expert knowledge is required. Active Learning (AL) is one approach to mitigate the problem of limited labeled data. Through selecting the most informative and representative data instances for labeling, AL can contribute to more efficient learning of the model. Recent AL methods for CNNs propose different solutions for the selection of instances to be labeled. However, they do not perform consistently well and are often computationally expensive. In this paper, we propose a novel AL algorithm that efficiently learns from unlabeled data by capturing high prediction uncertainty. By replacing the softmax standard output of a CNN with the parameters of a Dirichlet density, the model learns to identify data instances that contribute efficiently to improving model performance during training. We demonstrate in several experiments with publicly available data that our method consistently outperforms other state-of-the-art AL approaches. It can be easily implemented and does not require extensive computational resources for training. Additionally, we are able to show the benefits of the approach on a real-world medical use case in the field of automated detection of visual signals for pneumonia on chest radiographs.

READ FULL TEXT

page 1

page 7

research
05/22/2019

Dual Active Sampling on Batch-Incremental Active Learning

Recently, Convolutional Neural Networks (CNNs) have shown unprecedented ...
research
10/13/2022

TiDAL: Learning Training Dynamics for Active Learning

Active learning (AL) aims to select the most useful data samples from an...
research
08/17/2021

ImitAL: Learning Active Learning Strategies from Synthetic Data

One of the biggest challenges that complicates applied supervised machin...
research
05/07/2022

Towards Computationally Feasible Deep Active Learning

Active learning (AL) is a prominent technique for reducing the annotatio...
research
07/03/2023

REAL: A Representative Error-Driven Approach for Active Learning

Given a limited labeling budget, active learning (AL) aims to sample the...
research
08/13/2021

Jasmine: A New Active Learning Approach to Combat Cybercrime

Over the past decade, the advent of cybercrime has accelarated the resea...
research
08/26/2021

Consistent Relative Confidence and Label-Free Model Selection for Convolutional Neural Networks

This paper is concerned with image classification based on deep convolut...

Please sign up or login with your details

Forgot password? Click here to reset