Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 162 tok/s
Gemini 2.5 Pro 51 tok/s Pro
GPT-5 Medium 31 tok/s Pro
GPT-5 High 28 tok/s Pro
GPT-4o 95 tok/s Pro
Kimi K2 202 tok/s Pro
GPT OSS 120B 425 tok/s Pro
Claude Sonnet 4.5 36 tok/s Pro
2000 character limit reached

Stream-based Active Learning by Exploiting Temporal Properties in Perception with Temporal Predicted Loss (2309.05517v2)

Published 11 Sep 2023 in cs.CV and cs.LG

Abstract: Active learning (AL) reduces the amount of labeled data needed to train a machine learning model by intelligently choosing which instances to label. Classic pool-based AL requires all data to be present in a datacenter, which can be challenging with the increasing amounts of data needed in deep learning. However, AL on mobile devices and robots, like autonomous cars, can filter the data from perception sensor streams before reaching the datacenter. We exploited the temporal properties for such image streams in our work and proposed the novel temporal predicted loss (TPL) method. To evaluate the stream-based setting properly, we introduced the GTA V streets and the A2D2 streets dataset and made both publicly available. Our experiments showed that our approach significantly improves the diversity of the selection while being an uncertainty-based method. As pool-based approaches are more common in perception applications, we derived a concept for comparing pool-based and stream-based AL, where TPL out-performed state-of-the-art pool- or stream-based approaches for different models. TPL demonstrated a gain of 2.5 precept points (pp) less required data while being significantly faster than pool-based methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. Deep batch active learning by diverse, uncertain gradient lower bounds. In Proceeding of International Conference on Learning Representations (ICLR), 2020.
  2. The power of ensembles for active learning in image classification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
  3. Temporal coherence for active learning in videos. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2019.
  4. Stream-based active learning with linear models. Knowledge-Based Systems, 254, 10 2022. ISSN 09507051. 10.1016/j.knosys.2022.109664.
  5. Sequential graph convolutional network for active learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9583–9592, 2021.
  6. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision (ECCV), September 2018.
  7. Incremental semi-supervised learning from streams for object classification. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 5743–5749, 2018.
  8. The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2016. URL www.cityscapes-dataset.net.
  9. Episode-based active learning with bayesian neural networks. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, volume 2017-July, pages 498–500, 2017. ISBN 9781538607336. 10.1109/CVPRW.2017.75.
  10. Imagenet: A large-scale hierarchical image database. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), pages 248–255, 2009.
  11. Deep active learning for efficient training of a lidar 3d object detector. In Proceedings of the IEEE Intelligent Vehicles Symposium (IV), pages 667–674, 2019.
  12. Bayesian active learning for sim-to-real robotic perception. In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022.
  13. Budgeted stream-based active learning via adaptive submodular maximization. In Proceedings of Neural Information Processing Systems, 2016.
  14. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33th International Conference on International Conference on Machine Learning (ICML), page 1050–1059, 2016.
  15. Are we ready for autonomous driving? the kitti vision benchmark suite. In Proceedings of the IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2012. URL www.cvlibs.net/datasets/kitti.
  16. A2d2: Audi autonomous driving dataset. arXiv, 2004.06320, 2020. URL https://www.a2d2.audi.
  17. Deep residual learning for image recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
  18. Efficient active learning strategies for monocular 3d object detection. In Proceedings of the IEEE Intelligent Vehicles Symposium (IV), 2022.
  19. Bayesian active learning for classification and preference learning. arXiv, 1112.5745, 2011.
  20. Efficient uncertainty estimation for semantic segmentation in videos. In Proceedings of the European Conference on Computer Vision (ECCV), 2018.
  21. Submodular streaming in all its glory: Tight approximation, minimum memory and low adaptive complexity. In Proceedings of the 36th International Conference on Machine Learning (ICML), pages 3311–3320. PMLR, 2019.
  22. Task-aware variational adversarial active learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8166–8175, 2021.
  23. Batchbald: Efficient and diverse batch acquisition for deep bayesian active learning. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, pages 7026–7037, 2019.
  24. Learning multiple layers of features from tiny images. Technical report, Canadian Institute for Advanced Research, 2009. URL http://www.cs.toronto.edu/~kriz/cifar.html.
  25. Stream-based active learning for efficient and adaptive classification of 3d objects. In proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2016.
  26. Pytorch: An imperative style, high-performance deep learning library. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors, In Proceedings of the International Conference on Neural Information Processing Systems, pages 8024–8035. Curran Associates, Inc., 2019.
  27. Stream-based active learning for sliding windows under the influence of verification latency. Machine Learning, 111(6):2011–2036, Jun 2022. ISSN 1573-0565. 10.1007/s10994-021-06099-z. URL https://doi.org/10.1007/s10994-021-06099-z.
  28. Distributed active learning for semantic segmentation on walking robots. In Proceedings of the 20th International Conference on Advanced Robotics (ICAR), pages 461–467. Institute of Electrical and Electronics Engineers Inc., 2021. ISBN 9781665436847. 10.1109/ICAR53236.2021.9659389.
  29. A survey of deep active learning. ACM Computing Surveys (CSUR), 54:1 – 40, 2022.
  30. The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), volume 2016-December, pages 3234–3243, 12 2016.
  31. Advanced active learning strategies for object detection. In Proceedings of the IEEE Intelligent Vehicles Symposium (IV), pages 871–876, 2020.
  32. Active learning for convolutional neural networks: A core-set approach. In Proceedings of the International Conference on Learning Representations (ICLR), 8 2018.
  33. Active learning for deep neural networks on edge devices. ArXiv, 2106.10836, 2021.
  34. Burr Settles. Active learning literature survey. Technical report, University of Wisconsin–Madison, 2010.
  35. Very deep convolutional networks for large-scale image recognition. In Proceedings of the International Conference on Learning Representations (ICLR), 2015.
  36. Variational adversarial active learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 3 2019.
  37. Learning loss for active learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
  38. Active learning with abstaining classifiers for imbalanced drifting data streams. In Proceedings of the IEEE International Conference on Big Data, 2019.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up