mlsanityData to 14 Oct 2026

Streaming Active Learning with Deep Neural Networks

arXiv 2303.02535 ↗First posted 5 Mar 2023cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

Active learning is perhaps most naturally posed as an online learning problem. However, prior active learning approaches with deep neural networks assume offline access to the entire dataset ahead of time. This paper proposes VeSSAL, a new algorithm for batch active learning with deep neural networks in streaming settings, which samples groups of points to query for labels at the moment they are encountered. Our approach trades off between uncertainty and diversity of queried samples to match a desired query rate without requiring any hand-tuned hyperparameters. Altogether, we expand the applicability of deep neural networks to realistic active learning scenarios, such as applications relevant to HCI and large, fractured datasets.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 24 of its 62 references that are in the map. First posted on arXiv 5 Mar 2023.

Builds on

24 of 62 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  6. 2017Deep Bayesian Active Learning with Image Datacited by 819
  7. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  8. 2020A Survey of Deep Active Learningcited by 554
  9. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 158
  10. 2019Discriminative Active Learningcited by 98
  11. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  12. 2017Deep Active Learning over the Long Tailcited by 84
12 more
  1. 2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
  2. 2014Minimax Analysis of Active Learningcited by 61
  3. 2018Active Learning for Deep Object Detectioncited by 50
  4. 2022Information-theoretic Online Memory Selection for Continual Learningcited by 42
  5. 2017Active Learning for Cost-Sensitive Classificationcited by 41
  6. 2021Wanderlust: Online Continual Object Detection in the Real Worldcited by 34
  7. 2020Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervisioncited by 32
  8. 2016Crowdsourcing in Computer Visioncited by 31
  9. 2015Efficient and Parsimonious Agnostic Active Learningcited by 17
  10. 2022Improved Algorithms for Neural Active Learningcited by 11
  11. 2021Active Learning for Deep Neural Networks on Edge Devicescited by 6
  12. 2013Relative Errors for Deterministic Low-Rank Matrix Approximationscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 8; 2025: 6; 2026: 4.

20 papers.

Sort:

By area:

  1. 2024Active Test-Time Adaptation: Theoretical Analyses and An Algorithmcited by 18
  2. 2025Representation-Based Exploration for Language Models: From Test-Time to Post-Trainingcited by 16
  3. 2024Generative Active Learning for Long-tailed Instance Segmentationcited by 10
  4. 2024Active Label Correction for Semantic Segmentation with Foundation Modelscited by 7
  5. 2025Towards Active Synthetic Data Generation for Finetuning Language Modelscited by 6
  6. 2026Active Testing of Large Language Models via Approximate Neyman Allocationcited by 5
  7. 2023Learning to Rank for Active Learning via Multi-Task Bilevel Optimizationcited by 3
  8. 2023Few Clicks Suffice: Active Test-Time Adaptation for Semantic Segmentationcited by 3
  9. 2024Weakly Supervised Test-Time Domain Adaptation for Object Detectioncited by 3
  10. 2025Towards Multimodal Active Learning: Efficient Learning with Limited Paired Datacited by 3
  11. 2024Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selectioncited by 2
  12. 2024Sparse Uncertainty-Informed Sampling from Federated Streaming Datacited by 2
8 more
  1. 2024Neural Active Learning Meets the Partial Monitoring Frameworkcited by 1
  2. 2024From Uncertainty to Clarity: Uncertainty-Guided Class-Incremental Learning for Limited Biomedical Samples via Semantic Expansioncited by 1
  3. 2025TAPS : Frustratingly Simple Test Time Active Learning for VLMscited by 1
  4. 2026Online Finetuning Decision Transformers with Pure RL Gradientscited by 1
  5. 2025Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptationcited by 0
  6. 2025brat: Aligned Multi-View Embeddings for Brain MRI Analysiscited by 0
  7. 2026Goal-Oriented Influence-Maximizing Data Acquisition for Learning and Optimizationcited by 0
  8. 2026QueryMarket: Cost-Aware Online Active Learning in Data Marketscited by 0