Disentanglement based Active Learning
Year: 2019
Type: preprint
Abstract: We propose Disentanglement based Active Learning (DAL), a new active learning technique based on query synthesis which leverages the concept of disentanglement. Instead of requesting labels from the human oracle, our method automatically labels majority of the datapoints, thus drastically reducing the human labelling budget in active learning. The proposed method uses Information Maximizing Generative Adversarial Nets (InfoGAN) to achieve the task where the active learner provides a feedback on the generation of InfoGAN based on which decision is taken about the datapoints to be queried. Results on two benchmark datasets demonstrate that DAL is able to achieve nearly fully supervised accuracy with fairly less labelling budget compared to existing active learning approaches.
Source: arXiv (Cornell University)
Authors: V S Silpa, K S Adarsh, S. Sumitra, Raju K. George
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2995743219