State-Relabeling Adversarial Active Learning

04/10/2020
by   Beichen Zhang, et al.
0

Active learning is to design label-efficient algorithms by sampling the most representative samples to be labeled by an oracle. In this paper, we propose a state relabeling adversarial active learning model (SRAAL), that leverages both the annotation and the labeled/unlabeled state information for deriving the most informative unlabeled samples. The SRAAL consists of a representation generator and a state discriminator. The generator uses the complementary annotation information with traditional reconstruction information to generate the unified representation of samples, which embeds the semantic into the whole data representation. Then, we design an online uncertainty indicator in the discriminator, which endues unlabeled samples with different importance. As a result, we can select the most informative samples based on the discriminator's predicted state. We also design an algorithm to initialize the labeled pool, which makes subsequent sampling more efficient. The experiments conducted on various datasets show that our model outperforms the previous state-of-art active learning methods and our initially sampling algorithm achieves better performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/18/2020

Minimax Active Learning

Active learning aims to develop label-efficient algorithms by querying t...
research
08/20/2021

Influence Selection for Active Learning

The existing active learning methods select the samples by evaluating th...
research
03/25/2023

Deep Active Learning with Contrastive Learning Under Realistic Data Pool Assumptions

Active learning aims to identify the most informative data from an unlab...
research
02/24/2021

Active Learning to Classify Macromolecular Structures in situ for Less Supervision in Cryo-Electron Tomography

Motivation: Cryo-Electron Tomography (cryo-ET) is a 3D bioimaging tool t...
research
03/31/2019

Variational Adversarial Active Learning

Active learning aims to develop label-efficient algorithms by sampling t...
research
07/23/2020

Deep Active Learning by Model Interpretability

Recent successes of Deep Neural Networks (DNNs) in a variety of research...
research
10/14/2020

Identifying Wrongly Predicted Samples: A Method for Active Learning

State-of-the-art machine learning models require access to significant a...

Please sign up or login with your details

Forgot password? Click here to reset