# MCDAL: Maximum Classifier Discrepancy for Active Learning

arXiv: https://arxiv.org/abs/2107.11049 · HTML: https://mlsanity.com/paper/2107.11049/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 60 references that are in the map.
- First posted on arXiv 23 Jul 2021.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Deep Co-Training for Semi-Supervised Image Recognition](https://mlsanity.com/paper/1803.05984/) (2018)
- [Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation](https://mlsanity.com/paper/1706.04737/) (2017)
- [Contextual Diversity for Active Learning](https://mlsanity.com/paper/2008.05723/) (2020)
- [BEGAN: Boundary Equilibrium Generative Adversarial Networks](https://mlsanity.com/paper/1703.10717/) (2017)
- [Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy](https://mlsanity.com/paper/1908.04951/) (2019)
- [Adversarial Dropout Regularization](https://mlsanity.com/paper/1711.01575/) (2017)
- [Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Network](https://mlsanity.com/paper/1806.05473/) (2018)
- [Detecting Human-Object Interactions with Action Co-occurrence Priors](https://mlsanity.com/paper/2007.08728/) (2020)
- [Generative Adversarial Active Learning](https://mlsanity.com/paper/1702.07956/) (2017)
- [Active Learning for Deep Detection Neural Networks](https://mlsanity.com/paper/1911.09168/) (2019)
- [State-Relabeling Adversarial Active Learning](https://mlsanity.com/paper/2004.04943/) (2020)
- [Adversarial Sampling for Active Learning](https://mlsanity.com/paper/1808.06671/) (2018)
- [Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approach](https://mlsanity.com/paper/1909.02201/) (2019)
- [Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection](https://mlsanity.com/paper/1809.02882/) (2018)

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

- [Active Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2303.08348/) (2023)
- [LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.05570/) (2021)
- [Feedback-guided Data Synthesis for Imbalanced Classification](https://mlsanity.com/paper/2310.00158/) (2023)
- [Unsupervised Selective Labeling for More Effective Semi-Supervised Learning](https://mlsanity.com/paper/2110.03006/) (2021)
- [PT4AL: Using Self-Supervised Pretext Tasks for Active Learning](https://mlsanity.com/paper/2201.07459/) (2022)
- [Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality](https://mlsanity.com/paper/2410.05210/) (2024)
- [Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learning](https://mlsanity.com/paper/2202.00195/) (2022)
- [Towards Inference Efficient Deep Ensemble Learning](https://mlsanity.com/paper/2301.12378/) (2023)
- [Single-Modal Entropy based Active Learning for Visual Question Answering](https://mlsanity.com/paper/2110.10906/) (2021)
- [Semi-Supervised Image Captioning by Adversarially Propagating Labeled Data](https://mlsanity.com/paper/2301.11174/) (2023)
- [Spectral Transfer Guided Active Domain Adaptation For Thermal Imagery](https://mlsanity.com/paper/2304.07031/) (2023)
- [Overcoming Overconfidence for Active Learning](https://mlsanity.com/paper/2308.10571/) (2023)
- [Federated Active Learning Framework for Efficient Annotation Strategy in Skin-lesion Classification](https://mlsanity.com/paper/2406.11310/) (2024)
- [Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection](https://mlsanity.com/paper/2409.11653/) (2024)
- [Distribution Discrepancy and Feature Heterogeneity for Active 3D Object Detection](https://mlsanity.com/paper/2409.05425/) (2024)
- [Towards Clinical Practice in CT-Based Pulmonary Disease Screening: An Efficient and Reliable Framework](https://mlsanity.com/paper/2412.01525/) (2024)
- [Decision Boundary Optimization-Informed Domain Adaptation](https://mlsanity.com/paper/2502.06498/) (2025)
- [Unsupervised Active Learning via Natural Feature Progressive Framework](https://mlsanity.com/paper/2510.04939/) (2025)

## Abstract (arXiv)

Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition; however, GAN is usually known to suffer from instability and sensitivity to hyper-parameters. In contrast to these methods, we propose in this paper a novel active learning framework that we call Maximum Classifier Discrepancy for Active Learning (MCDAL) which takes the prediction discrepancies between multiple classifiers. In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them. Intuitively, the discrepancies in the auxiliary classification layers' predictions indicate the uncertainty in the prediction. In this regard, we propose a novel method to leverage the classifier discrepancies for the acquisition function for active learning. We also provide an interpretation of our idea in relation to existing GAN based active learning methods and domain adaptation frameworks. Moreover, we empirically demonstrate the utility of our approach where the performance of our approach exceeds the state-of-the-art methods on several image classification and semantic segmentation datasets in active learning setups.