Large-Scale Visual Active Learning with Deep Probabilistic Ensembles
Annotating the right data for training deep neural networks is an important challenge. Active learning using uncertainty estimates from Bayesian Neural Networks (BNNs) could provide an effective solution to this. Despite being theoretically principled, BNNs require approximations to be applied to large-scale problems, and have not been used widely by practitioners. In this paper, we introduce Deep Probabilistic Ensembles (DPEs), a scalable technique that uses a regularized ensemble to approximate a deep BNN. We conduct a series of active learning experiments to evaluate DPEs on classification with the CIFAR-10, CIFAR-100 and ImageNet datasets, and semantic segmentation with the BDD100k dataset. Our models consistently outperform baselines and previously published methods, requiring significantly less training data to achieve competitive performances.
Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Kashyap Chitta (add twitter)
Jose M. Alvarez (edit)
Adam Lesnikowski (edit)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
None (add)
Repo:
None (add)
Stargazers:
0
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
0
Language:
None
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
11/08/18 06:01PM
7,265
2,354
Tweets
arxiv_cscv: Large-Scale Visual Active Learning with Deep Probabilistic Ensembles https://t.co/5Z9vAeHqeX
arxiv_cscv: Large-Scale Visual Active Learning with Deep Probabilistic Ensembles https://t.co/5Z9vAeHqeX
arxiv_cscv: Large-Scale Visual Active Learning with Deep Probabilistic Ensembles https://t.co/5Z9vAeHqeX
ComputerPapers: Large-Scale Visual Active Learning with Deep Probabilistic Ensembles. https://t.co/UbVC14cRpG
arxiv_cscv: Large-Scale Visual Active Learning with Deep Probabilistic Ensembles https://t.co/5Z9vAeHqeX
arxiv_cscv: Large-Scale Visual Active Learning with Deep Probabilistic Ensembles https://t.co/5Z9vAeHqeX
nmfeeds: [O] https://t.co/sU3wGlUeSL Large-Scale Visual Active Learning with Deep Probabilistic Ensembles. Annotating the right dat...
nmfeeds: [CV] https://t.co/sU3wGlUeSL Large-Scale Visual Active Learning with Deep Probabilistic Ensembles. Annotating the right da...
arxivml: "Large-Scale Visual Active Learning with Deep Probabilistic Ensembles", Kashyap Chitta, Jose M. Alvarez, Adam Lesni… https://t.co/qbrFKz9HU3
arxiv_cscv: Large-Scale Visual Active Learning with Deep Probabilistic Ensembles https://t.co/5Z9vAeHqeX
BrundageBot: Large-Scale Visual Active Learning with Deep Probabilistic Ensembles. Kashyap Chitta, Jose M. Alvarez, and Adam Lesnikowski https://t.co/xEGmx8VxVx
Images
Related