paper-with-me

Papers

QBDC: Query by dropout committee for training deep supervised architecture

2015-11-19 · Melanie Ducoffe, Frederic Precioso

While the current trend is to increase the depth of neural networks to increase their performance, the size of their training database has to grow accordingly. We notice an emergence of tremendous databases, although providing labels to build a training set still remains a very expensive task. We tackle the problem of selecting the samples to be labelled in an online fashion. In this paper, we present an active learning strategy based on query by committee and dropout technique to train a Convolutional Neural Network (CNN). We derive a commmittee of partial CNNs resulting from batchwise dropout runs on the initial CNN. We evaluate our active learning strategy for CNN on MNIST benchmark, showing in particular that selecting less than 30 % from the annotated database is enough to get similar error rate as using the full training set on MNIST. We also studied the robustness of our method against adversarial examples.

📄 PDF Abstract BibTeX arXiv:1511.06412

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Constraining the Parameters of High-Dimensional Models with Active Learning

2019-05-19 · Sascha Caron, Tom Heskes, Sydney Otten, Bob Stienen

Constraining the parameters of physical models with $>5-10$ parameters is a widespread problem in fields like particle physics and astronomy. The generation of data to explore this parameter space often requires large am…

Active LearningAstronomyVocal Bursts Intensity Prediction

Active Multitask Learning with Committees

2021-03-24 · Jingxi Xu, Da Tang, Tony Jebara

The cost of annotating training data has traditionally been a bottleneck for supervised learning approaches. The problem is further exacerbated when supervised learning is applied to a number of correlated tasks simultan…

Transfer Learning

Active Multitask Learning with Committees

2019-05-16 · ICML Workshop AMTL 2019 6 · Anonymous

The cost of annotating training data has traditionally been a bottleneck for supervised learning approaches. The problem is further exacerbated when supervised learning is applied to a number of correlated tasks simultan…

Transfer Learning

Efficient Diverse Ensemble for Discriminative Co-Tracking

2017-11-16 · CVPR 2018 6 · Kourosh Meshgi, Shigeyuki Oba, Shin Ishii

Ensemble discriminative tracking utilizes a committee of classifiers, to label data samples, which are in turn, used for retraining the tracker to localize the target using the collective knowledge of the committee. Comm…

Ensemble Learning

Structural query-by-committee

2018-03-17 · Christopher Tosh, Sanjoy Dasgupta

In this work, we describe a framework that unifies many different interactive learning tasks. We present a generalization of the {\it query-by-committee} active learning algorithm for this setting, and we study its consi…

Active Learning