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 160 tok/s
Gemini 2.5 Pro 50 tok/s Pro
GPT-5 Medium 33 tok/s Pro
GPT-5 High 41 tok/s Pro
GPT-4o 95 tok/s Pro
Kimi K2 193 tok/s Pro
GPT OSS 120B 417 tok/s Pro
Claude Sonnet 4.5 39 tok/s Pro
2000 character limit reached

A Cosine Similarity-based Method for Out-of-Distribution Detection (2306.14920v1)

Published 23 Jun 2023 in cs.LG

Abstract: The ability to detect OOD data is a crucial aspect of practical machine learning applications. In this work, we show that cosine similarity between the test feature and the typical ID feature is a good indicator of OOD data. We propose Class Typical Matching (CTM), a post hoc OOD detection algorithm that uses a cosine similarity scoring function. Extensive experiments on multiple benchmarks show that CTM outperforms existing post hoc OOD detection methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (29)
  1. Concrete problems in AI safety. CoRR, abs/1606.06565, 2016. URL http://arxiv.org/abs/1606.06565.
  2. Input similarity from the neural network perspective. Advances in Neural Information Processing Systems, 32, 2019.
  3. Describing textures in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  3606–3613, 2014.
  4. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pp.  248–255. Ieee, 2009.
  5. Is out-of-distribution detection learnable? In Oh, A. H., Agarwal, A., Belgrave, D., and Cho, K. (eds.), Advances in Neural Information Processing Systems, 2022. URL https://openreview.net/forum?id=sde_7ZzGXOE.
  6. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  770–778, 2016.
  7. A baseline for detecting misclassified and out-of-distribution examples in neural networks. Proceedings of International Conference on Learning Representations, 2017.
  8. Scaling out-of-distribution detection for real-world settings. In Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research, pp.  8759–8773. PMLR, 17–23 Jul 2022.
  9. Densely connected convolutional networks. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp.  4700–4708, 2017.
  10. On the importance of gradients for detecting distributional shifts in the wild. In Beygelzimer, A., Dauphin, Y., Liang, P., and Vaughan, J. W. (eds.), Advances in Neural Information Processing Systems, 2021. URL https://openreview.net/forum?id=fmiwLdJCmLS.
  11. Learning multiple layers of features from tiny images. Tech Report, 2009.
  12. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. In Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., and Garnett, R. (eds.), Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc., 2018a. URL https://proceedings.neurips.cc/paper_files/paper/2018/file/abdeb6f575ac5c6676b747bca8d09cc2-Paper.pdf.
  13. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. Advances in neural information processing systems, 31, 2018b.
  14. Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690, 2017.
  15. Energy-based out-of-distribution detection. In Advances in Neural Information Processing Systems (NeurIPS), 2020.
  16. Predictive uncertainty estimation via prior networks. In Proceedings of the Advances in Neural Information Processing Systems, pp.  7047–7058, 2018.
  17. How to exploit hyperspherical embeddings for out-of-distribution detection? In The Eleventh International Conference on Learning Representations, 2023. URL https://openreview.net/forum?id=aEFaE0W5pAd.
  18. Reading digits in natural images with unsupervised feature learning. NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 2011.
  19. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. CoRR, abs/1412.1897, 2014. URL http://arxiv.org/abs/1412.1897.
  20. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  4510–4520, 2018.
  21. Out-of-distribution detection with deep nearest neighbors. In International Conference on Machine Learning (ICML), 2022.
  22. The inaturalist species classification and detection dataset. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp.  8769–8778, 2018.
  23. Mitigating neural network overconfidence with logit normalization. Proceedings of the International Conference on Machine Learning, 2022.
  24. Sun database: Large-scale scene recognition from abbey to zoo. In 2010 IEEE computer society conference on computer vision and pattern recognition, pp.  3485–3492. IEEE, 2010.
  25. Turkergaze: Crowdsourcing saliency with webcam based eye tracking. arXiv preprint arXiv:1504.06755, 2015.
  26. Generalized out-of-distribution detection: A survey. arXiv preprint arXiv:2110.11334, 2021.
  27. Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365, 2015.
  28. Wide residual networks. arXiv preprint arXiv:1605.07146, 2016.
  29. Places: A 10 million image database for scene recognition. IEEE transactions on Pattern Analysis and Machine Intelligence, 40(6):1452–1464, 2017.
Citations (2)

Summary

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

Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

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

Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

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

List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

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