2020
DOI: 10.48550/arxiv.2012.08044
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Deep Bayesian Active Learning, A Brief Survey on Recent Advances

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(4 citation statements)
references
References 14 publications
0
4
0
Order By: Relevance
“…Several methods for uncertainty estimation have been used in active learning workflows such as entropy [43,47,49], empirical standard deviation with bootstrapping [53], Bayesian uncertainty estimation [54], least confidence [52], margin sampling [55], and mutual information [43]. In this work, the uncertainty is estimated by computing the standard deviation of prediction values generated from the ensemble of models.…”
Section: Discussionmentioning
confidence: 99%
“…Several methods for uncertainty estimation have been used in active learning workflows such as entropy [43,47,49], empirical standard deviation with bootstrapping [53], Bayesian uncertainty estimation [54], least confidence [52], margin sampling [55], and mutual information [43]. In this work, the uncertainty is estimated by computing the standard deviation of prediction values generated from the ensemble of models.…”
Section: Discussionmentioning
confidence: 99%
“…On the other hand, sequential training of such expressive models as well as extending the framework to high dimensional data injects even more complexity [4,5,6]. This challenge was relatively underexplored, until a breakthrough work by Gal et al [7], which essentially considered the problem of incorporating deep learning into AL for high dimensional data as highly connected with that of uncertainty representation [8]. They thus approached the problem from the perspective of uncertainty representation in deep learning for AL, and developed a Bayesian AL framework for image data.…”
Section: Introductionmentioning
confidence: 99%
“…One major concern in existing model-based approaches [1], [2] is how to capture the appropriate prior information about the complex structure of the underlying tissues and how to incorporate this prior knowledge into the image reconstruction scheme. By the advent of deep neural networks (DNNs) [3], various end-to-end learning-based methods [4][5][6][7][8] have been proposed which try to learn both the physical model and the prior information about the underlying tissues. These methods lead to many shortcomings such as very large number of training pairs requirements and no-guaranteed solutions consistent with the true physical models.…”
Section: Introductionmentioning
confidence: 99%