# Rethinking deep active learning: Using unlabeled data at model training

arXiv: https://arxiv.org/abs/1911.08177 · HTML: https://mlsanity.com/paper/1911.08177/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2019.

## Built on by (most cited first, 30 of 39)

- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets](https://mlsanity.com/paper/2202.02794/) (2022)
- [Active Learning Through a Covering Lens](https://mlsanity.com/paper/2205.11320/) (2022)
- [Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach](https://mlsanity.com/paper/2106.02968/) (2021)
- [Active Learning at the ImageNet Scale](https://mlsanity.com/paper/2111.12880/) (2021)
- [Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection](https://mlsanity.com/paper/2106.11921/) (2021)
- [Making Your First Choice: To Address Cold Start Problem in Vision Active Learning](https://mlsanity.com/paper/2210.02442/) (2022)
- [Warm Start Active Learning with Proxy Labels & Selection via Semi-Supervised Fine-Tuning](https://mlsanity.com/paper/2209.06285/) (2022)
- [LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning](https://mlsanity.com/paper/2306.09910/) (2023)
- [Revisiting Active Learning in the Era of Vision Foundation Models](https://mlsanity.com/paper/2401.14555/) (2024)
- [Minority Class Oriented Active Learning for Imbalanced Datasets](https://mlsanity.com/paper/2202.00390/) (2022)
- [Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learning](https://mlsanity.com/paper/2307.08415/) (2023)
- [Making Better Use of Unlabelled Data in Bayesian Active Learning](https://mlsanity.com/paper/2404.17249/) (2024)
- [COLosSAL: A Benchmark for Cold-start Active Learning for 3D Medical Image Segmentation](https://mlsanity.com/paper/2307.12004/) (2023)
- [Model-Change Active Learning in Graph-Based Semi-Supervised Learning](https://mlsanity.com/paper/2110.07739/) (2021)
- [ALWOD: Active Learning for Weakly-Supervised Object Detection](https://mlsanity.com/paper/2309.07914/) (2023)
- [Deep Active Learning for Computer Vision: Past and Future](https://mlsanity.com/paper/2211.14819/) (2022)
- [Diverse Complexity Measures for Dataset Curation in Self-driving](https://mlsanity.com/paper/2101.06554/) (2021)
- [Multi-Domain Active Learning: Literature Review and Comparative Study](https://mlsanity.com/paper/2106.13516/) (2021)
- [Poisson Reweighted Laplacian Uncertainty Sampling for Graph-based Active Learning](https://mlsanity.com/paper/2210.15786/) (2022)
- [A Survey on Active Deep Learning: From Model-driven to Data-driven](https://mlsanity.com/paper/2101.09933/) (2021)
- [Query Complexity of Active Learning for Function Family With Nearly Orthogonal Basis](https://mlsanity.com/paper/2306.03356/) (2023)
- [Training Ensembles with Inliers and Outliers for Semi-supervised Active Learning](https://mlsanity.com/paper/2307.03741/) (2023)
- [Semi-Supervised Variational Adversarial Active Learning via Learning to Rank and Agreement-Based Pseudo Labeling](https://mlsanity.com/paper/2408.12774/) (2024)
- [AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language Models](https://mlsanity.com/paper/2112.08787/) (2021)
- [cRedAnno+: Annotation Exploitation in Self-Explanatory Lung Nodule Diagnosis](https://mlsanity.com/paper/2210.16097/) (2022)
- [Combining Self-labeling with Selective Sampling](https://mlsanity.com/paper/2301.04420/) (2023)
- [CALICO: Confident Active Learning with Integrated Calibration](https://mlsanity.com/paper/2407.02335/) (2024)
- [Using Sum-Product Networks to Assess Uncertainty in Deep Active Learning](https://mlsanity.com/paper/2206.09798/) (2022)
- [Improving Semi-supervised Deep Learning by using Automatic Thresholding to Deal with Out of Distribution Data for COVID-19 Detection using Chest X-ray Images](https://mlsanity.com/paper/2211.02142/) (2022)

## Abstract (arXiv)

Active learning typically focuses on training a model on few labeled examples alone, while unlabeled ones are only used for acquisition. In this work we depart from this setting by using both labeled and unlabeled data during model training across active learning cycles. We do so by using unsupervised feature learning at the beginning of the active learning pipeline and semi-supervised learning at every active learning cycle, on all available data. The former has not been investigated before in active learning, while the study of latter in the context of deep learning is scarce and recent findings are not conclusive with respect to its benefit. Our idea is orthogonal to acquisition strategies by using more data, much like ensemble methods use more models. By systematically evaluating on a number of popular acquisition strategies and datasets, we find that the use of unlabeled data during model training brings a surprising accuracy improvement in image classification, compared to the differences between acquisition strategies. We thus explore smaller label budgets, even one label per class.