Task-Aware Variational Adversarial Active Learning
arXiv:2002.04709
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.
arXiv comment14 pages, 13 figures, 1 table
References in corpus (10)
- Scikit-learn: Machine Learning in Python
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Conditional Generative Adversarial Nets
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- YouTube-8M: A Large-Scale Video Classification Benchmark
- Bayesian Active Learning for Classification and Preference Learning
- BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
- Bayesian Batch Active Learning as Sparse Subset Approximation
- Bayesian Generative Active Deep Learning
- Active Learning for Decision-Making from Imbalanced Observational Data