Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Advancing Out-of-Distribution Detection through Data Purification and Dynamic Activation Function Design (2403.03412v1)

Published 6 Mar 2024 in cs.LG and cs.CV

Abstract: In the dynamic realms of machine learning and deep learning, the robustness and reliability of models are paramount, especially in critical real-world applications. A fundamental challenge in this sphere is managing Out-of-Distribution (OOD) samples, significantly increasing the risks of model misclassification and uncertainty. Our work addresses this challenge by enhancing the detection and management of OOD samples in neural networks. We introduce OOD-R (Out-of-Distribution-Rectified), a meticulously curated collection of open-source datasets with enhanced noise reduction properties. In-Distribution (ID) noise in existing OOD datasets can lead to inaccurate evaluation of detection algorithms. Recognizing this, OOD-R incorporates noise filtering technologies to refine the datasets, ensuring a more accurate and reliable evaluation of OOD detection algorithms. This approach not only improves the overall quality of data but also aids in better distinguishing between OOD and ID samples, resulting in up to a 2.5\% improvement in model accuracy and a minimum 3.2\% reduction in false positives. Furthermore, we present ActFun, an innovative method that fine-tunes the model's response to diverse inputs, thereby improving the stability of feature extraction and minimizing specificity issues. ActFun addresses the common problem of model overconfidence in OOD detection by strategically reducing the influence of hidden units, which enhances the model's capability to estimate OOD uncertainty more accurately. Implementing ActFun in the OOD-R dataset has led to significant performance enhancements, including an 18.42\% increase in AUROC of the GradNorm method and a 16.93\% decrease in FPR95 of the Energy method. Overall, our research not only advances the methodologies in OOD detection but also emphasizes the importance of dataset integrity for accurate algorithm evaluation.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Discriminative out-of-distribution detection for semantic segmentation, 2018.
  2. Robust out-of-distribution detection via informative outlier mining. arXiv preprint arXiv:2006.15207, 1(2):7, 2020.
  3. Generative ensembles for robust anomaly detection. 2018.
  4. Describing textures in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3606–3613, 2014.
  5. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
  6. Repvgg: Making vgg-style convnets great again. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13733–13742, 2021.
  7. Density estimation using real nvp. arXiv preprint arXiv:1605.08803, 2016.
  8. The open world assumption. In eSI Workshop: The Closed World of Databases meets the Open World of the Semantic Web, volume 15, page 1, 2006.
  9. Selectivenet: A deep neural network with an integrated reject option, 2019.
  10. Scaling out-of-distribution detection for real-world settings. arXiv preprint arXiv:1911.11132, 2019.
  11. A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136, 2016.
  12. Deep anomaly detection with outlier exposure. arXiv preprint arXiv:1812.04606, 2018.
  13. Natural adversarial examples. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15262–15271, 2021.
  14. Generalized odin: Detecting out-of-distribution image without learning from out-of-distribution data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10951–10960, 2020.
  15. Mos: Towards scaling out-of-distribution detection for large semantic space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8710–8719, 2021.
  16. Stacked generative adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5077–5086, 2017.
  17. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  18. Why normalizing flows fail to detect out-of-distribution data. Advances in neural information processing systems, 33:20578–20589, 2020.
  19. Visual odometry based on stereo image sequences with ransac-based outlier rejection scheme. In 2010 ieee intelligent vehicles symposium, pages 486–492. IEEE, 2010.
  20. Big transfer (bit): General visual representation learning. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part V 16, pages 491–507. Springer, 2020.
  21. Training confidence-calibrated classifiers for detecting out-of-distribution samples. arXiv preprint arXiv:1711.09325, 2017.
  22. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. Advances in neural information processing systems, 31, 2018.
  23. Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690, 2017.
  24. Mood: Multi-level out-of-distribution detection, 2021.
  25. Energy-based out-of-distribution detection. Advances in neural information processing systems, 33:21464–21475, 2020.
  26. Predictive uncertainty estimation via prior networks, 2018.
  27. Self-supervised learning for generalizable out-of-distribution detection. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 5216–5223, 2020.
  28. Do deep generative models know what they don’t know? arXiv preprint arXiv:1810.09136, 2018.
  29. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 427–436, 2015.
  30. Outlier exposure with confidence control for out-of-distribution detection. Neurocomputing, 441:138–150, 2021.
  31. Likelihood ratios for out-of-distribution detection. Advances in neural information processing systems, 32, 2019.
  32. Stochastic backpropagation and approximate inference in deep generative models. In International conference on machine learning, pages 1278–1286. PMLR, 2014.
  33. Understanding anomaly detection with deep invertible networks through hierarchies of distributions and features. Advances in Neural Information Processing Systems, 33:21038–21049, 2020.
  34. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In International conference on information processing in medical imaging, pages 146–157. Springer, 2017.
  35. Input complexity and out-of-distribution detection with likelihood-based generative models. arXiv preprint arXiv:1909.11480, 2019.
  36. Confidence estimation in deep neural networks via density modelling. arXiv preprint arXiv:1707.07013, 2017.
  37. React: Out-of-distribution detection with rectified activations. Advances in Neural Information Processing Systems, 34:144–157, 2021.
  38. A family of nonparametric density estimation algorithms. Communications on Pure and Applied Mathematics, 66(2):145–164, 2013.
  39. Conditional image generation with pixelcnn decoders. Advances in neural information processing systems, 29, 2016.
  40. The inaturalist species classification and detection dataset. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8769–8778, 2018.
  41. Vim: Out-of-distribution with virtual-logit matching. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 4921–4930, 2022.
  42. Further analysis of outlier detection with deep generative models. Advances in Neural Information Processing Systems, 33:8982–8992, 2020.
  43. Sun database: Large-scale scene recognition from abbey to zoo. In 2010 IEEE computer society conference on computer vision and pattern recognition, pages 3485–3492. IEEE, 2010.
  44. Likelihood regret: An out-of-distribution detection score for variational auto-encoder. Advances in neural information processing systems, 33:20685–20696, 2020.
  45. Generalized out-of-distribution detection: A survey. arxiv. arXiv preprint arXiv:2110.11334, 2021.
  46. Openood: Benchmarking generalized out-of-distribution detection. Advances in Neural Information Processing Systems, 35:32598–32611, 2022.
  47. Places: A 10 million image database for scene recognition. IEEE transactions on pattern analysis and machine intelligence, 40(6):1452–1464, 2017.
  48. Rethinking out-of-distribution detection from a human-centric perspective. arXiv preprint arXiv:2211.16778, 2022.
  49. Boosting out-of-distribution detection with typical features. Advances in Neural Information Processing Systems, 35:20758–20769, 2022.
  50. Rethinking adversarial transferability from a data distribution perspective. In International Conference on Learning Representations, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Yingrui Ji (5 papers)
  2. Yao Zhu (49 papers)
  3. Zhigang Li (61 papers)
  4. Jiansheng Chen (41 papers)
  5. Yunlong Kong (2 papers)
  6. Jingbo Chen (7 papers)

Summary

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

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