mlsanityData to 7 Oct 2026

Mitigating Sampling Bias and Improving Robustness in Active Learning

arXiv 2109.06321 ↗First posted 13 Sep 2021cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

This paper presents simple and efficient methods to mitigate sampling bias in active learning while achieving state-of-the-art accuracy and model robustness. We introduce supervised contrastive active learning by leveraging the contrastive loss for active learning under a supervised setting. We propose an unbiased query strategy that selects informative data samples of diverse feature representations with our methods: supervised contrastive active learning (SCAL) and deep feature modeling (DFM). We empirically demonstrate our proposed methods reduce sampling bias, achieve state-of-the-art accuracy and model calibration in an active learning setup with the query computation 26x faster than Bayesian active learning by disagreement and 11x faster than CoreSet. The proposed SCAL method outperforms by a big margin in robustness to dataset shift and out-of-distribution.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 28 of its 56 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

28 of 56 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  9. 2020Supervised Contrastive Learningcited by 2,803
  10. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  11. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  12. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
16 more
  1. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  2. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  3. 2017Deep Bayesian Active Learning with Image Datacited by 812
  4. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  5. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  6. 2019Learning Loss for Active Learningcited by 335
  7. 2019Cyclical Stochastic Gradient MCMC for Bayesian Deep Learningcited by 203
  8. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 155
  9. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 145
  10. 2020Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertaintycited by 128
  11. 2020Improving model calibration with accuracy versus uncertainty optimizationcited by 123
  12. 2017Deep Active Learning for Named Entity Recognitioncited by 108
  13. 2019Deep Active Learning: Unified and Principled Method for Query and Trainingcited by 92
  14. 2015A Deeper Look at Dataset Biascited by 86
  15. 2021On Statistical Bias In Active Learning: How and When To Fix Itcited by 72
  16. 2019Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detectioncited by 39

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 0; 2025: 2.

5 papers.

  1. 2023D-CALM: A Dynamic Clustering-based Active Learning Approach for Mitigating Biascited by 12
  2. 2023Active Learning with Combinatorial Coveragecited by 3
  3. 2023Overcoming Overconfidence for Active Learningcited by 3
  4. 2025DEUCE: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learningcited by 2
  5. 2025Dependency-aware Maximum Likelihood Estimation for Active Learningcited by 0