mlsanityData to 7 Oct 2026

Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision

arXiv 2003.00393 ↗First posted 1 Mar 2020cs.CV cs.AIcited by 32

Not on the map. Why?

Abstract (arXiv)

Active learning (AL) aims to minimize labeling efforts for data-demanding deep neural networks (DNNs) by selecting the most representative data points for annotation. However, currently used methods are ill-equipped to deal with biased data. The main motivation of this paper is to consider a realistic setting for pool-based semi-supervised AL, where the unlabeled collection of train data is biased. We theoretically derive an optimal acquisition function for AL in this setting. It can be formulated as distribution shift minimization between unlabeled train data and weakly-labeled validation dataset. To implement such acquisition function, we propose a low-complexity method for feature density matching using self-supervised Fisher kernel (FK) as well as several novel pseudo-label estimators. Our FK-based method outperforms state-of-the-art methods on MNIST, SVHN, and ImageNet classification while requiring only 1/10th of processing. The conducted experiments show at least 40% drop in labeling efforts for the biased class-imbalanced data compared to existing methods.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 6; 2023: 8; 2024: 5; 2025: 3; 2026: 3.

32 papers.

Sort:

By area:

  1. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
  2. 2021Multiple instance active learning for object detectioncited by 77
  3. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 53
  4. 2021Improving Contrastive Learning on Imbalanced Seed Data via Open-World Samplingcited by 30
  5. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26
  6. 2023Streaming Active Learning with Deep Neural Networkscited by 20
  7. 2022Improving the Intra-class Long-tail in 3D Detection via Rare Example Miningcited by 19
  8. 2021Which images to label for few-shot medical landmark detection?cited by 16
  9. 2022Knowledge-Aware Federated Active Learning with Non-IID Datacited by 15
  10. 2021AutoDO: Robust AutoAugment for Biased Data with Label Noise via Scalable Probabilistic Implicit Differentiationcited by 14
  11. 2022A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Taskscited by 12
  12. 2023D-CALM: A Dynamic Clustering-based Active Learning Approach for Mitigating Biascited by 12
20 more
  1. 2024Making Better Use of Unlabelled Data in Bayesian Active Learningcited by 10
  2. 2023Concurrent Misclassification and Out-of-Distribution Detection for Semantic Segmentation via Energy-Based Normalizing Flowcited by 8
  3. 2023BaSAL: Size-Balanced Warm Start Active Learning for LiDAR Semantic Segmentationcited by 8
  4. 2021CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentationcited by 6
  5. 2022Efficient Human-in-the-loop System for Guiding DNNs Attentioncited by 4
  6. 2024VLMine: Long-Tail Data Mining with Vision Language Modelscited by 4
  7. 2021Just Label What You Need: Fine-Grained Active Selection for Perception and Prediction through Partially Labeled Scenescited by 2
  8. 2022Optimizing Active Learning for Low Annotation Budgetscited by 2
  9. 2023A Pre-trained Data Deduplication Model based on Active Learningcited by 2
  10. 2023How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learningcited by 2
  11. 2022Can I see an Example? Active Learning the Long Tail of Attributes and Relationscited by 1
  12. 2024STONE: A Submodular Optimization Framework for Active 3D Object Detectioncited by 1
  13. 2023Open-CRB: Towards Open World Active Learning for 3D Object Detectioncited by 0
  14. 2024ALVIN: Active Learning Via INterpolationcited by 0
  15. 2025Dependency-aware Maximum Likelihood Estimation for Active Learningcited by 0
  16. 2025HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detectioncited by 0
  17. 2025Exploring Active Learning for Semiconductor Defect Segmentationcited by 0
  18. 2026Goal-Oriented Influence-Maximizing Data Acquisition for Learning and Optimizationcited by 0
  19. 2026Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learningcited by 0
  20. 2026Does Model Uncertainty Track Human Ambiguity? Evidence from Multi-Annotator Vision Benchmarkscited by 0