# VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning

arXiv: https://arxiv.org/abs/2003.11249 · HTML: https://mlsanity.com/paper/2003.11249/

## Key facts

- Cited by 25 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 25 Mar 2020.

## Built on by (most cited first, 25 of 25)

- [Active Learning by Feature Mixing](https://mlsanity.com/paper/2203.07034/) (2022)
- [A Survey on Deep Active Learning: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.00334/) (2024)
- [Reducing Label Effort: Self-Supervised meets Active Learning](https://mlsanity.com/paper/2108.11458/) (2021)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [A Systematic Review on Long-Tailed Learning](https://mlsanity.com/paper/2408.00483/) (2024)
- [Learning Distinctive Margin toward Active Domain Adaptation](https://mlsanity.com/paper/2203.05738/) (2022)
- [Class-Balanced Active Learning for Image Classification](https://mlsanity.com/paper/2110.04543/) (2021)
- [Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation](https://mlsanity.com/paper/2408.12483/) (2024)
- [Accelerating Neural Field Training via Soft Mining](https://mlsanity.com/paper/2312.00075/) (2023)
- [Supervised Anomaly Detection via Conditional Generative Adversarial Network and Ensemble Active Learning](https://mlsanity.com/paper/2104.11952/) (2021)
- [CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2112.05975/) (2021)
- [REAL: A Representative Error-Driven Approach for Active Learning](https://mlsanity.com/paper/2307.00968/) (2023)
- [Overcoming Overconfidence for Active Learning](https://mlsanity.com/paper/2308.10571/) (2023)
- [Downstream-Pretext Domain Knowledge Traceback for Active Learning](https://mlsanity.com/paper/2407.14720/) (2024)
- [How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learning](https://mlsanity.com/paper/2308.08224/) (2023)
- [Active Learning for Fine-Grained Sketch-Based Image Retrieval](https://mlsanity.com/paper/2309.08743/) (2023)
- [Can I see an Example? Active Learning the Long Tail of Attributes and Relations](https://mlsanity.com/paper/2203.06215/) (2022)
- [Transfer and Active Learning for Dissonance Detection: Addressing the Rare-Class Challenge](https://mlsanity.com/paper/2305.02459/) (2023)
- [Learning Objective-Specific Active Learning Strategies with Attentive Neural Processes](https://mlsanity.com/paper/2309.05477/) (2023)
- [Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction](https://mlsanity.com/paper/2205.11279/) (2022)
- [Active Vision Reinforcement Learning under Limited Visual Observability](https://mlsanity.com/paper/2306.00975/) (2023)
- [Active Learning for Finely-Categorized Image-Text Retrieval by Selecting Hard Negative Unpaired Samples](https://mlsanity.com/paper/2405.16301/) (2024)
- [Active Learning Methods for Efficient Data Utilization and Model Performance Enhancement](https://mlsanity.com/paper/2504.16136/) (2025)
- [When Imbalance Comes Twice: Active Learning under Simulated Class Imbalance and Label Shift in Binary Semantic Segmentation](https://mlsanity.com/paper/2601.06209/) (2026)
- [Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning](https://mlsanity.com/paper/2607.13555/) (2026)

## Abstract (arXiv)

Active Learning for discriminative models has largely been studied with the focus on individual samples, with less emphasis on how classes are distributed or which classes are hard to deal with. In this work, we show that this is harmful. We propose a method based on the Bayes' rule, that can naturally incorporate class imbalance into the Active Learning framework. We derive that three terms should be considered together when estimating the probability of a classifier making a mistake for a given sample; i) probability of mislabelling a class, ii) likelihood of the data given a predicted class, and iii) the prior probability on the abundance of a predicted class. Implementing these terms requires a generative model and an intractable likelihood estimation. Therefore, we train a Variational Auto Encoder (VAE) for this purpose. To further tie the VAE with the classifier and facilitate VAE training, we use the classifiers' deep feature representations as input to the VAE. By considering all three probabilities, among them especially the data imbalance, we can substantially improve the potential of existing methods under limited data budget. We show that our method can be applied to classification tasks on multiple different datasets -- including one that is a real-world dataset with heavy data imbalance -- significantly outperforming the state of the art.