# Minimax Active Learning

arXiv: https://arxiv.org/abs/2012.10467 · HTML: https://mlsanity.com/paper/2012.10467/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2020.

## Built on by (most cited first, 18 of 18)

- [BayesFormer: Transformer with Uncertainty Estimation](https://mlsanity.com/paper/2206.00826/) (2022)
- [Active Learning Strategies for Weakly-supervised Object Detection](https://mlsanity.com/paper/2207.12112/) (2022)
- [Semantic Segmentation with Active Semi-Supervised Learning](https://mlsanity.com/paper/2203.10730/) (2022)
- [Knowledge-Aware Federated Active Learning with Non-IID Data](https://mlsanity.com/paper/2211.13579/) (2022)
- [A Simple Baseline for Low-Budget Active Learning](https://mlsanity.com/paper/2110.12033/) (2021)
- [Making Better Use of Unlabelled Data in Bayesian Active Learning](https://mlsanity.com/paper/2404.17249/) (2024)
- [An Informative Path Planning Framework for Active Learning in UAV-based Semantic Mapping](https://mlsanity.com/paper/2302.03347/) (2023)
- [Deep Active Ensemble Sampling For Image Classification](https://mlsanity.com/paper/2210.05770/) (2022)
- [Multi-Domain Active Learning: Literature Review and Comparative Study](https://mlsanity.com/paper/2106.13516/) (2021)
- [Minimax Optimization: The Case of Convex-Submodular](https://mlsanity.com/paper/2111.01262/) (2021)
- [Active Learning for Object Detection with Non-Redundant Informative Sampling](https://mlsanity.com/paper/2307.08414/) (2023)
- [Low-Regret Active learning](https://mlsanity.com/paper/2104.02822/) (2021)
- [Semantic Segmentation with Active Semi-Supervised Representation Learning](https://mlsanity.com/paper/2210.08403/) (2022)
- [MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detection](https://mlsanity.com/paper/2212.02804/) (2022)
- [Region-level Active Detector Learning](https://mlsanity.com/paper/2108.09186/) (2021)
- [Training Ensembles with Inliers and Outliers for Semi-supervised Active Learning](https://mlsanity.com/paper/2307.03741/) (2023)
- [ADROIT: A Self-Supervised Framework for Learning Robust Representations for Active Learning](https://mlsanity.com/paper/2503.07506/) (2025)
- [Active Learning with Task-Driven Representations for Messy Pools](https://mlsanity.com/paper/2510.25926/) (2025)

## Abstract (arXiv)

Active learning aims to develop label-efficient algorithms by querying the most representative samples to be labeled by a human annotator. Current active learning techniques either rely on model uncertainty to select the most uncertain samples or use clustering or reconstruction to choose the most diverse set of unlabeled examples. While uncertainty-based strategies are susceptible to outliers, solely relying on sample diversity does not capture the information available on the main task. In this work, we develop a semi-supervised minimax entropy-based active learning algorithm that leverages both uncertainty and diversity in an adversarial manner. Our model consists of an entropy minimizing feature encoding network followed by an entropy maximizing classification layer. This minimax formulation reduces the distribution gap between the labeled/unlabeled data, while a discriminator is simultaneously trained to distinguish the labeled/unlabeled data. The highest entropy samples from the classifier that the discriminator predicts as unlabeled are selected for labeling. We evaluate our method on various image classification and semantic segmentation benchmark datasets and show superior performance over the state-of-the-art methods.