mlsanityData to 14 Oct 2026

Deep Active Learning over the Long Tail

arXiv 1711.00941 ↗First posted 2 Nov 2017cs.LGcited by 84

Not on the map. Why?

Abstract (arXiv)

This paper is concerned with pool-based active learning for deep neural networks. Motivated by coreset dataset compression ideas, we present a novel active learning algorithm that queries consecutive points from the pool using farthest-first traversals in the space of neural activation over a representation layer. We show consistent and overwhelming improvement in sample complexity over passive learning (random sampling) for three datasets: MNIST, CIFAR-10, and CIFAR-100. In addition, our algorithm outperforms the traditional uncertainty sampling technique (obtained using softmax activations), and we identify cases where uncertainty sampling is only slightly better than random sampling.

Key facts. Cited by 84 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 6; 2022: 21; 2023: 20; 2024: 22; 2025: 7; 2026: 8.

84 papers.

Sort:

By area:

  1. 2021Active Learning by Acquiring Contrastive Examplescited by 156
  2. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 133
  3. 2022A Comparative Survey of Deep Active Learningcited by 89
  4. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  5. 2022Active Learning Through a Covering Lenscited by 66
  6. 2024Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approachcited by 50
  7. 2022A Framework and Benchmark for Deep Batch Active Learning for Regressioncited by 49
  8. 2022A Survey of Active Learning for Natural Language Processingcited by 40
  9. 2022GALAXY: Graph-based Active Learning at the Extremecited by 29
  10. 2021Cartography Active Learningcited by 26
  11. 2022A Lagrangian Duality Approach to Active Learningcited by 24
  12. 2022ALLSH: Active Learning Guided by Local Sensitivity and Hardnesscited by 23
38 more
  1. 2024An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Modelscited by 23
  2. 2023Multi-Resolution Active Learning of Fourier Neural Operatorscited by 22
  3. 2024Active Learning for Neural PDE Solverscited by 22
  4. 2022Batch Multi-Fidelity Active Learning with Budget Constraintscited by 20
  5. 2023ScatterShot: Interactive In-context Example Curation for Text Transformationcited by 20
  6. 2023Streaming Active Learning with Deep Neural Networkscited by 20
  7. 2023On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learningcited by 20
  8. 2025From Selection to Generation: A Survey of LLM-based Active Learningcited by 19
  9. 2023Algorithm Selection for Deep Active Learning with Imbalanced Datasetscited by 18
  10. 2022Active Learning Strategies for Weakly-supervised Object Detectioncited by 17
  11. 2023Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learningcited by 16
  12. 2022Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learningcited by 14
  13. 2023Re-thinking Federated Active Learning based on Inter-class Diversitycited by 14
  14. 2023Black-Box Batch Active Learning for Regressioncited by 12
  15. 2023Towards Distribution-Agnostic Generalized Category Discoverycited by 12
  16. 2023Gaussian Switch Sampling: A Second Order Approach to Active Learningcited by 10
  17. 2024Generative Active Learning for Long-tailed Instance Segmentationcited by 10
  18. 2023On the Limitations of Simulating Active Learningcited by 9
  19. 2023FOCAL: A Cost-Aware Video Dataset for Active Learningcited by 9
  20. 2023Improved Algorithm for Deep Active Learning under Imbalance via Optimal Separationcited by 8
  21. 2022A Survey on AI Sustainability: Emerging Trends on Learning Algorithms and Research Challengescited by 7
  22. 2022Deep Active Learning for Computer Vision: Past and Futurecited by 7
  23. 2024Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitionscited by 7
  24. 2024AHA: Human-Assisted Out-of-Distribution Generalization and Detectioncited by 7
  25. 2022Neural Design for Genetic Perturbation Experimentscited by 6
  26. 2023You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentationcited by 6
  27. 2026When Self-Belief Misleads: Active Label Acquisition for Reinforcement Learning with Verifiable Rewardscited by 6
  28. 2021Active Learning of Neural Collision Handler for Complex 3D Mesh Deformationscited by 5
  29. 2022Neural Active Learning on Heteroskedastic Distributionscited by 5
  30. 2022A Federated Approach to Predicting Emojis in Hindi Tweetscited by 5
  31. 2023FedABC: Targeting Fair Competition in Personalized Federated Learningcited by 5
  32. 2023Deep Active Learning in the Presence of Label Noise: A Surveycited by 5
  33. 2023Alleviating the Long-Tail Problem in Conversational Recommender Systemscited by 5
  34. 2024Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learningcited by 5
  35. 2024Deep Active Learning in the Open Worldcited by 5
  36. 2024Generative Active Learning for Image Synthesis Personalizationcited by 4
  37. 2024Feasibility Study on Active Learning of Smart Surrogates for Scientific Simulationscited by 4
  38. 2025Revisiting Automatic Data Curation for Vision Foundation Models in Digital Pathologycited by 4

50 most cited of 84 All 84 (JSON)