Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings (2312.15086v1)

Published 22 Dec 2023 in cs.LG and cs.CV

Abstract: Out-of-distribution (OOD) detection is an important topic for real-world machine learning systems, but settings with limited in-distribution samples have been underexplored. Such few-shot OOD settings are challenging, as models have scarce opportunities to learn the data distribution before being tasked with identifying OOD samples. Indeed, we demonstrate that recent state-of-the-art OOD methods fail to outperform simple baselines in the few-shot setting. We thus propose a hypernetwork framework called HyperMix, using Mixup on the generated classifier parameters, as well as a natural out-of-episode outlier exposure technique that does not require an additional outlier dataset. We conduct experiments on CIFAR-FS and MiniImageNet, significantly outperforming other OOD methods in the few-shot regime.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (66)
  1. Low data drug discovery with one-shot learning. ACS central science, 2017.
  2. Concrete problems in ai safety. arXiv preprint arXiv:1606.06565, 2016.
  3. Self-driving cars: A survey. Expert Systems with Applications, 2021.
  4. Improved few-shot visual classification. In CVPR, 2020.
  5. Learning from few samples: A survey. arXiv preprint arXiv:2007.15484, 2020.
  6. Meta-learning with differentiable closed-form solvers. ICLR, 2019.
  7. Learning feed-forward one-shot learners. In Advances in neural information processing systems, 2016.
  8. Single layer predictive normalized maximum likelihood for out-of-distribution detection. Advances in Neural Information Processing Systems, 34, 2021.
  9. Guillotine regularization: Improving deep networks generalization by removing their head. arXiv preprint arXiv:2206.13378, 2022.
  10. A closer look at few-shot classification. arXiv preprint arXiv:1904.04232, 2019.
  11. Multi-level semantic feature augmentation for one-shot learning. IEEE Transactions on Image Processing, 2019.
  12. Imagenet: A large-scale hierarchical image database. In IEEE conference on computer vision and pattern recognition, 2009.
  13. Reducing network agnostophobia. Advances in Neural Information Processing Systems, 31, 2018.
  14. FROB: Few-shot ROBust model for classification with out-of-distribution detection, 2022.
  15. Ego4D: Around the World in 3,000 Hours of Egocentric Video. CVPR, 2022.
  16. Model-agnostic meta-learning for fast adaptation of deep networks. In International conference on machine learning, 2017.
  17. Exploring the limits of out-of-distribution detection. Advances in Neural Information Processing Systems, 34, 2021.
  18. On the modularity of hypernetworks. Advances in Neural Information Processing Systems, 2020.
  19. Boosting few-shot visual learning with self-supervision. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pages 8058–8067, 2019.
  20. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572, 2014.
  21. Hypernetworks. In ICLR, 2017.
  22. Co-teaching: Robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems, 2018.
  23. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016.
  24. Why relu networks yield high-confidence predictions far away from the training data and how to mitigate the problem. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 41–50, 2019.
  25. A baseline for detecting misclassified and out-of-distribution examples in neural networks. Proceedings of International Conference on Learning Representations, 2017.
  26. Deep anomaly detection with outlier exposure. arXiv preprint arXiv:1812.04606, 2018.
  27. Training sar-atr models for reliable operation in open-world environments. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021.
  28. Ood-maml: Meta-learning for few-shot out-of-distribution detection and classification. In Advances in Neural Information Processing Systems, 2020.
  29. Alex Krizhevsky et al. Learning multiple layers of features from tiny images, 2009.
  30. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, 2012.
  31. Adversarial examples in the physical world. In Artificial intelligence safety and security, 2018.
  32. Poodle: Improving few-shot learning via penalizing out-of-distribution samples. Advances in Neural Information Processing Systems, 2021.
  33. Training confidence-calibrated classifiers for detecting out-of-distribution samples. International Conference on Learning Representations, 2018.
  34. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In Advances in neural information processing systems, 2018.
  35. Adversarial feature hallucination networks for few-shot learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.
  36. Few-shot learning with noisy labels. In CVPR, 2022.
  37. Toward automatic threat recognition for airport x-ray baggage screening with deep convolutional object detection. arXiv preprint arXiv:1912.06329, 2019.
  38. Enhancing the reliability of out-of-distribution image detection in neural networks. In International Conference on Learning Representations, 2018.
  39. Charting the right manifold: Manifold mixup for few-shot learning. 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 2207–2216, 2020.
  40. Deterministic neural networks with appropriate inductive biases capture epistemic and aleatoric uncertainty. arXiv preprint arXiv:2102.11582, 2021.
  41. Posterior calibration and exploratory analysis for natural language processing models. In EMNLP, 2015.
  42. Tadam: Task dependent adaptive metric for improved few-shot learning. In Advances in neural information processing systems, 2018.
  43. Incremental few-shot object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020.
  44. Self-supervised knowledge distillation for few-shot learning. ArXiv, abs/2006.09785, 2020.
  45. Revisiting linear decision boundaries for few-shot learning with transformer hypernetworks, 2021.
  46. Hypershot: Few-shot learning by kernel hypernetworks. arXiv preprint arXiv:2203.11378, 2022.
  47. Prototypical networks for few-shot learning. In Advances in Neural Information Processing Systems, 2017.
  48. Learning to compare: Relation network for few-shot learning. In CVPR, 2018.
  49. On the importance of initialization and momentum in deep learning. In Proceedings of the 30th International Conference on Machine Learning, 2013.
  50. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199, 2013.
  51. A meta-learning perspective on cold-start recommendations for items. Advances in neural information processing systems, 2017.
  52. Manifold mixup: Better representations by interpolating hidden states. In International Conference on Machine Learning, 2019.
  53. Out-of-distribution detection in classifiers via generation. arXiv preprint arXiv:1910.04241, 2019.
  54. Matching networks for one shot learning. In Advances in Neural Information Processing Systems, 2016.
  55. Ai in health: state of the art, challenges, and future directions. Yearbook of medical informatics, 2019.
  56. Few-shot out-of-distribution detection. In ICML Workshop on Uncertainty and Robustness in Deep Learning, 2020.
  57. Few-shot out-of-distribution detection. In International Conference on Machine Learning (ICML) Workshop on Uncertainty and Robustness in Deep Learning, 2020.
  58. Tafe-net: Task-aware feature embeddings for low shot learning. In CVPR, 2019.
  59. Generalizing from a few examples: A survey on few-shot learning. ACM Computing Surveys, 2020.
  60. Contrastive training for improved out-of-distribution detection. arXiv preprint arXiv:2007.05566, 2020.
  61. Generalized out-of-distribution detection: A survey. arXiv preprint arXiv:2110.11334, 2021.
  62. Sylph: A hypernetwork framework for incremental few-shot object detection. In CVPR, 2022.
  63. Deepemd: Few-shot image classification with differentiable earth mover’s distance and structured classifiers. In CVPR, 2020.
  64. mixup: Beyond empirical risk minimization. In International Conference on Learning Representations, 2018.
  65. Fine-grained out-of-distribution detection with mixup outlier exposure. arXiv preprint arXiv:2106.03917, 2021.
  66. Person re-identification: Past, present and future. arXiv preprint arXiv:1610.02984, 2016.
Citations (2)
View on Semantic Scholar

Summary

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

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

Tweets