Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 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

Learning by Erasing: Conditional Entropy based Transferable Out-Of-Distribution Detection (2204.11041v3)

Published 23 Apr 2022 in cs.CV

Abstract: Out-of-distribution (OOD) detection is essential to handle the distribution shifts between training and test scenarios. For a new in-distribution (ID) dataset, existing methods require retraining to capture the dataset-specific feature representation or data distribution. In this paper, we propose a deep generative models (DGM) based transferable OOD detection method, which is unnecessary to retrain on a new ID dataset. We design an image erasing strategy to equip exclusive conditional entropy distribution for each ID dataset, which determines the discrepancy of DGM's posteriori ucertainty distribution on different ID datasets. Owing to the powerful representation capacity of convolutional neural networks, the proposed model trained on complex dataset can capture the above discrepancy between ID datasets without retraining and thus achieve transferable OOD detection. We validate the proposed method on five datasets and verity that ours achieves comparable performance to the state-of-the-art group based OOD detection methods that need to be retrained to deploy on new ID datasets. Our code is available at https://github.com/oOHCIOo/CETOOD.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. BBC. 2020. AI “Outperforms” Doctors Diagnosing Breast Cancer. https://www.bbc.com/news/health-50857759. Accessed: 2020-01-02.
  2. Discriminative out-of-distribution detection for semantic segmentation. CoRR.
  3. Out-of-distribution Detection via Frequency-regularized Generative Models. In IEEE Winter Conference on Applications of Computer Vision (WACV).
  4. MP3: A Unified Model To Map, Perceive, Predict and Plan. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  5. The relationship between Precision-Recall and ROC curves. In International Conference on Machine Learning (ICML).
  6. ImageNet: A large-scale hierarchical image database. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  7. Extremely Simple Activation Shaping for Out-of-Distribution Detection. In International Conference on Learning Representations (ICLR).
  8. A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks. In International Conference on Learning Representations (ICLR).
  9. Deep Anomaly Detection with Outlier Exposure. In International Conference on Learning Representations (ICLR).
  10. Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  11. Feature Space Singularity for Out-of-Distribution Detection. In Proceedings of the Workshop on Artificial Intelligence.
  12. MOS: Towards Scaling Out-of-Distribution Detection for Large Semantic Space. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  13. Revisiting flow generative models for Out-of-distribution detection. In International Conference on Learning Representations (ICLR).
  14. XProtoNet: Diagnosis in Chest Radiography With Global and Local Explanations. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  15. Why Normalizing Flows Fail to Detect Out-of-Distribution Data. In Advances in Neural Information Processing Systems (NeurIPS).
  16. Learning multiple layers of features from tiny images. Handbook of Systemic Autoimmune Diseases.
  17. Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles. In Advances in Neural Information Processing Systems (NeurIPS).
  18. Gradient-based learning applied to document recognition. Proceedings of the IEEE.
  19. Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples. In International Conference on Learning Representations (ICLR).
  20. A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks. In Advances in Neural Information Processing Systems (NeurIPS).
  21. Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks. In International Conference on Learning Representations (ICLR).
  22. Deep Learning Face Attributes in the Wild. In IEEE International Conference on Computer Vision (ICCV).
  23. How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection? In International Conference on Learning Representations (ICLR).
  24. Self-Supervised Learning for Generalizable Out-of-Distribution Detection. In AAAI Conference on Artificial Intelligence (AAAI).
  25. Detecting Out-of-Distribution Inputs to Deep Generative Models Using a Test for Typicality. CoRR.
  26. Reading Digits in Natural Images with Unsupervised Feature Learning. In Workshop on Deep Learning and Unsupervised Feature Learning (NeurIPS workshop).
  27. Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  28. A Cosine Similarity-based Method for Out-of-Distribution Detection. CoRR.
  29. Likelihood Ratios for Out-of-Distribution Detection. In Advances in Neural Information Processing Systems (NeurIPS).
  30. PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications. In International Conference on Learning Representations (ICLR).
  31. Evidential Deep Learning to Quantify Classification Uncertainty. In Advances in Neural Information Processing Systems (NeurIPS).
  32. Input Complexity and Out-of-distribution Detection with Likelihood-based Generative Models. In International Conference on Learning Representations (ICLR).
  33. Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max Layers. In International Conference on Learning Representations (ICLR).
  34. SR-OOD: Out-of-Distribution Detection via Sample Repairing. CoRR.
  35. Times, T. N. Y. 2018. After Fatal Uber Crash, a Self-Driving Start-Up Moves Forward. https://www.nytimes.com/2018/05/07/technology/uber-crash-autonomous-driveai.html. Accessed: 2018-05-07.
  36. The information bottleneck method. CoRR.
  37. Natural-Parameter Networks: A Class of Probabilistic Neural Networks. In Lee, D. D.; Sugiyama, M.; von Luxburg, U.; Guyon, I.; and Garnett, R., eds., Advances in Neural Information Processing Systems (NeurIPS).
  38. Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. CoRR.
  39. Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder. In Advances in Neural Information Processing Systems (NeurIPS).
  40. Out-of-Distribution Detection Using Union of 1-Dimensional Subspaces. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
  41. Understanding Failures in Out-of-Distribution Detection with Deep Generative Models. In International Conference on Machine Learning (ICML).
  42. Out-of-Distribution Detection with Distance Guarantee in Deep Generative Models. CoRR.

Summary

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

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