mlsanityData to 7 Oct 2026

Efficacy of Bayesian Neural Networks in Active Learning

arXiv 2104.00896 ↗First posted 2 Apr 2021cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Obtaining labeled data for machine learning tasks can be prohibitively expensive. Active learning mitigates this issue by exploring the unlabeled data space and prioritizing the selection of data that can best improve the model performance. A common approach to active learning is to pick a small sample of data for which the model is most uncertain. In this paper, we explore the efficacy of Bayesian neural networks for active learning, which naturally models uncertainty by learning distribution over the weights of neural networks. By performing a comprehensive set of experiments, we show that Bayesian neural networks are more efficient than ensemble based techniques in capturing uncertainty. Our findings also reveal some key drawbacks of the ensemble techniques, which was recently shown to be more effective than Monte Carlo dropouts.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 17 of its 29 references that are in the map. First posted on arXiv 2 Apr 2021.

Builds on

17 of 29 references.

References · 17

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2017On Calibration of Modern Neural Networkscited by 4,860
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  7. 2017Deep Bayesian Active Learning with Image Datacited by 812
  8. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 711
  9. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  10. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 359
  11. 2017Variational Dropout Sparsifies Deep Neural Networkscited by 265
  12. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 145
5 more
  1. 2017Bayesian Compression for Deep Learningcited by 116
  2. 2020Towards Robust and Reproducible Active Learning Using Neural Networkscited by 53
  3. 2017Active Learning for Convolutional Neural Networks: A Core-Set Approachcited by 34
  4. 2020Bayesian active learning for production, a systematic study and a reusable librarycited by 15
  5. 2016House price estimation from visual and textual featurescited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 0; 2025: 1; 2026: 4.

6 papers.

  1. 2023Active Prompt Learning in Vision Language Modelscited by 25
  2. 2026The Speed-up Factor: A Quantitative Multi-Iteration Active Learning Performance Metriccited by 1
  3. 2025PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Modelscited by 0
  4. 2026Active learning for photonic crystalscited by 0
  5. 2026Are Candidate Models Really Needed for Active Learning?cited by 0
  6. 2026Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learningcited by 0