Task-Aware Variational Adversarial Active Learning

TL;DR

This paper introduces TA-VAAL, a novel active learning method that combines task-aware and data distribution considerations using a ranking-based generative adversarial network to select informative samples efficiently.

Contribution

It proposes a task-aware variational adversarial active learning framework that improves sample selection by integrating ranking loss and data distribution modeling.

Findings

TA-VAAL outperforms state-of-the-art methods on various benchmarks.

It effectively handles balanced and imbalanced classification tasks.

The method is also successful in semantic segmentation applications.

Abstract

Often, labeling large amount of data is challenging due to high labeling cost limiting the application domain of deep learning techniques. Active learning (AL) tackles this by querying the most informative samples to be annotated among unlabeled pool. Two promising directions for AL that have been recently explored are task-agnostic approach to select data points that are far from the current labeled pool and task-aware approach that relies on the perspective of task model. Unfortunately, the former does not exploit structures from tasks and the latter does not seem to well-utilize overall data distribution. Here, we propose task-aware variational adversarial AL (TA-VAAL) that modifies task-agnostic VAAL, that considered data distribution of both label and unlabeled pools, by relaxing task learning loss prediction to ranking loss prediction and by using ranking conditional generative adversarial network to embed normalized ranking loss information on VAAL. Our proposed TA-VAAL outperforms state-of-the-arts on various benchmark datasets for classifications with balanced / imbalanced labels as well as semantic segmentation and its task-aware and task-agnostic AL properties were confirmed with our in-depth analyses.