Adversarial Active Learning for Deep Networks: a Margin Based Approach

02/27/2018
by   Mélanie Ducoffe, et al.
0

We propose a new active learning strategy designed for deep neural networks. The goal is to minimize the number of data annotation queried from an oracle during training. Previous active learning strategies scalable for deep networks were mostly based on uncertain sample selection. In this work, we focus on examples lying close to the decision boundary. Based on theoretical works on margin theory for active learning, we know that such examples may help to considerably decrease the number of annotations. While measuring the exact distance to the decision boundaries is intractable, we propose to rely on adversarial examples. We do not consider anymore them as a threat instead we exploit the information they provide on the distribution of the input space in order to approximate the distance to decision boundaries. We demonstrate empirically that adversarial active queries yield faster convergence of CNNs trained on MNIST, the Shoe-Bag and the Quick-Draw datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/22/2021

Exploring Adversarial Examples for Efficient Active Learning in Machine Learning Classifiers

Machine learning researchers have long noticed the phenomenon that the m...
research
03/20/2017

Active Decision Boundary Annotation with Deep Generative Models

This paper is on active learning where the goal is to reduce the data an...
research
10/16/2021

Deep Active Learning by Leveraging Training Dynamics

Active learning theories and methods have been extensively studied in cl...
research
11/30/2018

Are All Training Examples Created Equal? An Empirical Study

Modern computer vision algorithms often rely on very large training data...
research
01/15/2021

Heating up decision boundaries: isocapacitory saturation, adversarial scenarios and generalization bounds

In the present work we study classifiers' decision boundaries via Browni...
research
11/02/2022

Neural Active Learning on Heteroskedastic Distributions

Models that can actively seek out the best quality training data hold th...
research
11/25/2017

An Adaptive Strategy for Active Learning with Smooth Decision Boundary

We present the first adaptive strategy for active learning in the settin...

Please sign up or login with your details

Forgot password? Click here to reset