Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
91 tokens/sec
GPT-4o
12 tokens/sec
Gemini 2.5 Pro Pro
o3 Pro
5 tokens/sec
GPT-4.1 Pro
15 tokens/sec
DeepSeek R1 via Azure Pro
33 tokens/sec
Gemini 2.5 Flash Deprecated
12 tokens/sec
2000 character limit reached

Active Class Selection for Few-Shot Class-Incremental Learning (2307.02641v1)

Published 5 Jul 2023 in cs.RO, cs.CV, and cs.LG

Abstract: For real-world applications, robots will need to continually learn in their environments through limited interactions with their users. Toward this, previous works in few-shot class incremental learning (FSCIL) and active class selection (ACS) have achieved promising results but were tested in constrained setups. Therefore, in this paper, we combine ideas from FSCIL and ACS to develop a novel framework that can allow an autonomous agent to continually learn new objects by asking its users to label only a few of the most informative objects in the environment. To this end, we build on a state-of-the-art (SOTA) FSCIL model and extend it with techniques from ACS literature. We term this model Few-shot Incremental Active class SeleCtiOn (FIASco). We further integrate a potential field-based navigation technique with our model to develop a complete framework that can allow an agent to process and reason on its sensory data through the FIASco model, navigate towards the most informative object in the environment, gather data about the object through its sensors and incrementally update the FIASco model. Experimental results on a simulated agent and a real robot show the significance of our approach for long-term real-world robotics applications.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. Ronald C Arkin. Motor schema—based mobile robot navigation. The International journal of robotics research, 8(4):92–112, 1989.
  2. Few-shot continual active learning by a robot. In Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho (eds.), Advances in Neural Information Processing Systems, 2022. URL https://openreview.net/forum?id=35I4narr5A.
  3. Centroid based concept learning for RGB-D indoor scene classification. British Machine Vision Conference (BMVC), 2020a.
  4. What am i allowed to do here?: Online learning of context-specific norms by pepper. In Alan R. Wagner, David Feil-Seifer, Kerstin S. Haring, Silvia Rossi, Thomas Williams, Hongsheng He, and Shuzhi Sam Ge (eds.), Social Robotics, pp.  220–231, Cham, 2020b. Springer International Publishing. ISBN 978-3-030-62056-1.
  5. Cognitively-inspired model for incremental learning using a few examples. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp.  222–223, 2020c.
  6. Tell me what this is: few-shot incremental object learning by a robot. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.  8344–8350. IEEE, 2020d.
  7. EEC: Learning to encode and regenerate images for continual learning. In International Conference on Learning Representations (ICLR), 2021.
  8. CBCL-PR: A cognitively inspired model for class-incremental learning in robotics. IEEE Transactions on Cognitive and Developmental Systems, 2023.
  9. Active class incremental learning for imbalanced datasets. In European Conference on Computer Vision, pp.  146–162. Springer, 2020.
  10. A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory, pp.  144–152, 1992.
  11. Active and incremental learning with weak supervision. KI-Künstliche Intelligenz, 34(2):165–180, 2020.
  12. End-to-end incremental learning. In The European Conference on Computer Vision (ECCV), September 2018.
  13. Online object and task learning via human robot interaction. In 2019 International Conference on Robotics and Automation (ICRA), pp.  2132–2138, May 2019.
  14. Learning without memorizing. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
  15. Podnet: Pooled outputs distillation for small-tasks incremental learning. In European Conference on Computer Vision, pp.  86–102. Springer, 2020.
  16. Elizabeth Gibney. Could machine learning fuel a reproducibility crisis in science? Nature.
  17. A formal basis for the heuristic determination of minimum cost paths. IEEE transactions on Systems Science and Cybernetics, 4(2):100–107, 1968.
  18. Distilling the knowledge in a neural network. In NIPS Deep Learning and Representation Learning Workshop, 2015.
  19. The malmo platform for artificial intelligence experimentation. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI’16, pp.  4246–4247. AAAI Press, 2016. ISBN 9781577357704.
  20. Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences, 114(13):3521–3526, 2017a.
  21. Overcoming catastrophic forgetting in neural networks. Proceedings of the National Academy of Sciences of the United States of America, 114(13):3521–3526, 2017b.
  22. A hierarchical grocery store image dataset with visual and semantic labels. In IEEE Winter Conference on Applications of Computer Vision (WACV), 2019.
  23. Donald E Knuth. Art of computer programming, volume 2: Seminumerical algorithms. Addison-Wesley Professional, 2014.
  24. Potential field methods and their inherent limitations for mobile robot navigation. In ICRA, volume 2, pp.  1398–1404, 1991.
  25. Probabilistic active learning for active class selection. arXiv preprint arXiv:2108.03891, 2021.
  26. Alex Krizhevsky et al. Learning multiple layers of features from tiny images. 2009.
  27. Z. Li and D. Hoiem. Learning without forgetting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(12):2935–2947, Dec 2018.
  28. Microsoft coco: Common objects in context. In European conference on computer vision, pp.  740–755. Springer, 2014.
  29. Active and incremental learning for semantic als point cloud segmentation. ISPRS journal of photogrammetry and remote sensing, 169:73–92, 2020.
  30. Active class selection. In European Conference on Machine Learning, pp.  640–647. Springer, 2007.
  31. Gradient episodic memory for continual learning. Advances in neural information processing systems, 30, 2017.
  32. Building concepts one episode at a time: The hippocampus and concept formation. Neuroscience Letters, 680:31–38, 2018.
  33. Distance-based image classification: Generalizing to new classes at near-zero cost. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(11):2624–2637, Nov 2013.
  34. Learning to remember: A synaptic plasticity driven framework for continual learning. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.  11321–11329, June 2019.
  35. iCaRL: Incremental classifier and representation learning. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017.
  36. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  779–788, 2016.
  37. Wandering within a world: Online contextualized few-shot learning. arXiv preprint arXiv:2007.04546, 2020.
  38. Burr Settles. Active learning literature survey. 2009.
  39. Viewal: Active learning with viewpoint entropy for semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.
  40. Few-shot class-incremental learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2020.
  41. BP Welford. Note on a method for calculating corrected sums of squares and products. Technometrics, 4(3):419–420, 1962.
  42. Caltech-ucsd birds 200. Technical Report CNS-TR-201, Caltech, 2010. URL /se3/wp-content/uploads/2014/09/WelinderEtal10_CUB-200.pdf,http://www.vision.caltech.edu/visipedia/CUB-200.html.
  43. Active class selection for arousal classification. In International Conference on Affective Computing and Intelligent Interaction, pp.  132–141. Springer, 2011.
  44. Large scale incremental learning. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
  45. Der: Dynamically expandable representation for class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.  3014–3023, June 2021.
  46. Learning loss for active learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
  47. The hippocampus and inferential reasoning: building memories to navigate future decisions. Frontiers in Human Neuroscience, 6, 2012. doi: 10.3389/fnhum.2012.00070.
  48. Deepemd: Few-shot image classification with differentiable earth mover’s distance and structured classifiers. In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2020.
  49. Few-shot incremental learning with continually evolved classifiers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.  12455–12464, June 2021.
  50. Pycil: A python toolbox for class-incremental learning, 2021.
  51. Forward compatible few-shot class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  9046–9056, 2022.
  52. Self-promoted prototype refinement for few-shot class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  6801–6810, 2021.
Citations (1)
View on Semantic Scholar

Summary

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

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