QBDC: Query by dropout committee for training deep supervised architecture
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Constraining the Parameters of High-Dimensional Models with Active Learning
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 PredictionActive Multitask Learning with Committees
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 LearningActive Multitask Learning with Committees
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 LearningEfficient Diverse Ensemble for Discriminative Co-Tracking
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 LearningStructural query-by-committee
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