# Deep Active Learning with Adaptive Acquisition

arXiv: https://arxiv.org/abs/1906.11471 · HTML: https://mlsanity.com/paper/1906.11471/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jun 2019.

## Built on by (most cited first, 17 of 17)

- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Boosting Active Learning via Improving Test Performance](https://mlsanity.com/paper/2112.05683/) (2021)
- [Label-Efficient Learning in Agriculture: A Comprehensive Review](https://mlsanity.com/paper/2305.14691/) (2023)
- [Adaptive Compressed Sensing with Diffusion-Based Posterior Sampling](https://mlsanity.com/paper/2407.08256/) (2024)
- [Computer Vision for Primate Behavior Analysis in the Wild](https://mlsanity.com/paper/2401.16424/) (2024)
- [Active Learning by Query by Committee with Robust Divergences](https://mlsanity.com/paper/2211.10013/) (2022)
- [FAL-CUR: Fair Active Learning using Uncertainty and Representativeness on Fair Clustering](https://mlsanity.com/paper/2209.12756/) (2022)
- [A Survey of Dataset Refinement for Problems in Computer Vision Datasets](https://mlsanity.com/paper/2210.11717/) (2022)
- [Deep Active Learning in the Presence of Label Noise: A Survey](https://mlsanity.com/paper/2302.11075/) (2023)
- [Deep reinforced active learning for multi-class image classification](https://mlsanity.com/paper/2206.13391/) (2022)
- [Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2406.04088/) (2024)
- [Propagating Variational Model Uncertainty for Bioacoustic Call Label Smoothing](https://mlsanity.com/paper/2210.10526/) (2022)
- [Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes](https://mlsanity.com/paper/2309.05477/) (2023)
- [OPAD: An Optimized Policy-based Active Learning Framework for Document Content Analysis](https://mlsanity.com/paper/2110.02069/) (2021)
- [Active Learning from the Web](https://mlsanity.com/paper/2210.08205/) (2022)
- [Image Classification with Deep Reinforcement Active Learning](https://mlsanity.com/paper/2412.19877/) (2024)
- [Label What Matters: Modality-Balanced and Difficulty-Aware Multimodal Active Learning](https://mlsanity.com/paper/2603.25107/) (2026)

## Abstract (arXiv)

Model selection is treated as a standard performance boosting step in many machine learning applications. Once all other properties of a learning problem are fixed, the model is selected by grid search on a held-out validation set. This is strictly inapplicable to active learning. Within the standardized workflow, the acquisition function is chosen among available heuristics a priori, and its success is observed only after the labeling budget is already exhausted. More importantly, none of the earlier studies report a unique consistently successful acquisition heuristic to the extent to stand out as the unique best choice. We present a method to break this vicious circle by defining the acquisition function as a learning predictor and training it by reinforcement feedback collected from each labeling round. As active learning is a scarce data regime, we bootstrap from a well-known heuristic that filters the bulk of data points on which all heuristics would agree, and learn a policy to warp the top portion of this ranking in the most beneficial way for the character of a specific data distribution. Our system consists of a Bayesian neural net, the predictor, a bootstrap acquisition function, a probabilistic state definition, and another Bayesian policy network that can effectively incorporate this input distribution. We observe on three benchmark data sets that our method always manages to either invent a new superior acquisition function or to adapt itself to the a priori unknown best performing heuristic for each specific data set.