mlsanityData to 7 Oct 2026

Camera clustering for scalable stream-based active distillation

arXiv 2404.10411 ↗First posted 16 Apr 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a scalable framework designed to craft efficient lightweight models for video object detection utilizing self-training and knowledge distillation techniques. We scrutinize methodologies for the ideal selection of training images from video streams and the efficacy of model sharing across numerous cameras. By advocating for a camera clustering methodology, we aim to diminish the requisite number of models for training while augmenting the distillation dataset. The findings affirm that proper camera clustering notably amplifies the accuracy of distilled models, eclipsing the methodologies that employ distinct models for each camera or a universal model trained on the aggregate camera data.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 54 references that are in the map. First posted on arXiv 16 Apr 2024.

Builds on

25 of 54 references.

References · 25

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  4. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  5. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 507
  6. 2019Learning Loss for Active Learningcited by 335
  7. 2019Robust Aggregation for Federated Learningcited by 314
  8. 2019Variational Adversarial Active Learningcited by 284
  9. 2021Knowledge distillation: A good teacher is patient and consistentcited by 255
  10. 2020Contextual Diversity for Active Learningcited by 139
  11. 2019Adversarially Robust Distillationcited by 124
  12. 2021Multiple instance active learning for object detectioncited by 77
13 more
  1. 2020Active Domain Adaptation via Clustering Uncertainty-weighted Embeddingscited by 71
  2. 2018Online Model Distillation for Efficient Video Inferencecited by 60
  3. 2023Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detectioncited by 39
  4. 2022Fast Multi-view Clustering via Ensembles: Towards Scalability, Superiority, and Simplicitycited by 28
  5. 2022Delta Distillation for Efficient Video Processingcited by 10
  6. 2022Stream-based active learning with linear modelscited by 9
  7. 2022Robust Active Distillationcited by 9
  8. 2022Designing and Training of Lightweight Neural Networks on Edge Devices using Early Halting in Knowledge Distillationcited by 7
  9. 2022Online Active Learning for Soft Sensor Development using Semi-Supervised Autoencoderscited by 6
  10. 2023Robust online active learningcited by 5
  11. 2021Streaming Machine Learning and Online Active Learning for Automated Visual Inspectioncited by 4
  12. 2023Group Distributionally Robust Knowledge Distillationcited by 3
  13. 2021Towards Automatic Model Specialization for Edge Video Analyticscited by 2

Built on by

Not cited yet.