Parting with Illusions about Deep Active Learning

by   Sudhanshu Mittal, et al.

Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Recently, deep active learning has shown success on various tasks. However, the conventional evaluation scheme used for deep active learning is below par. Current methods disregard some apparent parallel work in the closely related fields. Active learning methods are quite sensitive w.r.t. changes in the training procedure like data augmentation. They improve by a large-margin when integrated with semi-supervised learning, but barely perform better than the random baseline. We re-implement various latest active learning approaches for image classification and evaluate them under more realistic settings. We further validate our findings for semantic segmentation. Based on our observations, we realistically assess the current state of the field and propose a more suitable evaluation protocol.


page 7

page 8

page 9


Revisiting Deep Active Learning for Semantic Segmentation

Active learning automatically selects samples for annotation from a data...

Deep Active Learning in the Presence of Label Noise: A Survey

Deep active learning has emerged as a powerful tool for training deep le...

Active Learning for Speech Recognition: the Power of Gradients

In training speech recognition systems, labeling audio clips can be expe...

Toward Optimal Probabilistic Active Learning Using a Bayesian Approach

Gathering labeled data to train well-performing machine learning models ...

Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection

Deep learning for clinical applications is subject to stringent performa...

Overcoming Overconfidence for Active Learning

It is not an exaggeration to say that the recent progress in artificial ...

Sampling Bias in Deep Active Classification: An Empirical Study

The exploding cost and time needed for data labeling and model training ...

Please sign up or login with your details

Forgot password? Click here to reset