arrow
返回

Dual generative adversarial active learning

delete2021-01-20
delete11
PRE
AI
J
Jifeng Guo
Z
Zhiqi Pang
M
Miaoyuan Bai
P
Peijiao Xie
陈
陈宇 (Yu Chen) *
DOI:10.1007/s10489-020-02121-4delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
The purpose of active learning is to significantly reduce the cost of annotation while ensuring the good performance of the model. In this paper, we propose a novel active learning method based on the combination of pool and synthesis named dual generative adversarial active learning (DGAAL), which includes the functions of image generation and representation learning. This method includes two groups of generative adversarial network composed of a generator and two discriminators. One group is used for representation learning, and then this paper performs sampling based on the predicted value of the discriminator. The other group is used for image generation. The purpose is to generate samples which are similar to those obtained from sampling, so that samples with rich information can be fully utilized. In the sampling process, the two groups of network cooperate with each other to enable the generated samples to participate in sampling process, and to enable the discriminator for sampling to co-evolve. Thus, in the later stage of sampling, the problem of insufficient information for selecting samples based on the pool method is alleviated. In this paper, DGAAL is evaluated extensively on three data sets, and the results show that DGAAL not only has certain advantages over the existing methods in terms of model performance but can also further reduces the annotation cost.
Keyword:
Deep learning
Generative adversarial networks
Image generation
Active learning

期刊

Applied Intelligence 封面图
Applied Intelligence
IF:
3.5
论文数:
7.7K
被引数:
1.7W

机构

N
northeast forestry university - china
学者数:
0
论文数: 233
被引数: 0
引用论文

引用论文

Deep Active Learning for Surface Defect Detection深度主动学习在表面缺陷检测中的应用
errSENSORS
IF3.5
err2020-03-16
err27
errOAAI
errLv, Xiaoming; Duan, Fajie; Jiang, Jia-Jia; Fu, Xiao; Gan, Lin
err分享
err收藏
Does Natalizumab Induce or Aggravate Psoriasis? A Case Study and Review of the Literature
err2018-09-18
err0
errOAAI
errSakis Lambrianides; Evgenios Kinnis; Eleni Leonidou; Marios Pantzaris
err分享
err收藏
Parallel Lines I: Test for Parallelism
err1987-01-01
err0
PREAI
errRonald J. Tallarida; Rodney B. Murray
err分享
err收藏
学者 查看更多内容