mlsanityData to 14 Oct 2026

On the Query Strategies for Efficient Online Active Distillation

arXiv 2309.01612 ↗First posted 4 Sep 2023cs.CV cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Deep Learning (DL) requires lots of time and data, resulting in high computational demands. Recently, researchers employ Active Learning (AL) and online distillation to enhance training efficiency and real-time model adaptation. This paper evaluates a set of query strategies to achieve the best training results. It focuses on Human Pose Estimation (HPE) applications, assessing the impact of selected frames during training using two approaches: a classical offline method and a online evaluation through a continual learning approach employing knowledge distillation, on a popular state-of-the-art HPE dataset. The paper demonstrates the possibility of enabling training at the edge lightweight models, adapting them effectively to new contexts in real-time.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 14 of its 22 references that are in the map. First posted on arXiv 4 Sep 2023.

Builds on

14 of 22 references.

References · 14

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2016Densely Connected Convolutional Networkscited by 6,720
  3. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  4. 2019Green AIcited by 627
  5. 2019Learning Loss for Active Learningcited by 336
  6. 2018Fast Human Pose Estimationcited by 68
  7. 2018Online Model Distillation for Efficient Video Inferencecited by 60
  8. 2021A Survey on Green Deep Learningcited by 52
  9. 2020Real-Time Video Inference on Edge Devices via Adaptive Model Streamingcited by 29
  10. 2023Active learning for data streams: a surveycited by 29
  11. 2023Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecyclecited by 14
  12. 2020Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learningcited by 7
2 more
  1. 2023Online Distillation with Continual Learning for Cyclic Domain Shiftscited by 6
  2. 2023An Expanded Benchmark that Rediscovers and Affirms the Edge of Uncertainty Sampling for Active Learning in Tabular Datasetscited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streamscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2021Online Knowledge Distillation for Efficient Pose Estimation
  2. 2025A Coarse-to-Fine Human Pose Estimation Method based on Two-stage Distillation and Progressive Graph Neural Network
  3. 2022Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions
  4. 2024Active Data Curation Effectively Distills Large-Scale Multimodal Models
  5. 2021Boosting of Head Pose Estimation by Knowledge Distillation
  6. 2024Estimating Human Poses Across Datasets: A Unified Skeleton and Multi-Teacher Distillation Approach
  7. 2021Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation
  8. 2023Rethinking Momentum Knowledge Distillation in Online Continual Learning