Skip to main content

FINE-GRAIN INFERENCE ON OUT-OF-DISTRIBUTION DATA WITH HIERARCHICAL CLASSIFICATION

Publication ,  Conference
Linderman, R; Zhang, J; Inkawhich, N; Li, H; Chen, Y
Published in: Proceedings of Machine Learning Research
January 1, 2023

Machine learning methods must be trusted to make appropriate decisions in real-world environments, even when faced with out-of-distribution (OOD) samples. Many current approaches simply aim to detect OOD examples and alert the user when an unrecognized input is given. However, when the OOD sample significantly overlaps with the training data, a binary anomaly detection is not interpretable or explainable, and provides little information to the user. We propose a new model for OOD detection that makes predictions at varying levels of granularity—as the inputs become more ambiguous, the model predictions become coarser and more conservative. Consider an animal classifier that encounters an unknown bird species and a car. Both cases are OOD, but the user gains more information if the classifier recognizes that its uncertainty over the particular species is too large and predicts “bird” instead of detecting it as OOD. Furthermore, we diagnose the classifier’s performance at each level of the hierarchy improving the explainability and interpretability of the model’s predictions. We demonstrate the effectiveness of hierarchical classifiers for both fine- and coarse-grained OOD tasks. The code is available at https://github.com/rwl93/ hierarchical-ood.

Duke Scholars

Published In

Proceedings of Machine Learning Research

EISSN

2640-3498

Publication Date

January 1, 2023

Volume

232

Start / End Page

162 / 183
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Linderman, R., Zhang, J., Inkawhich, N., Li, H., & Chen, Y. (2023). FINE-GRAIN INFERENCE ON OUT-OF-DISTRIBUTION DATA WITH HIERARCHICAL CLASSIFICATION. In Proceedings of Machine Learning Research (Vol. 232, pp. 162–183).
Linderman, R., J. Zhang, N. Inkawhich, H. Li, and Y. Chen. “FINE-GRAIN INFERENCE ON OUT-OF-DISTRIBUTION DATA WITH HIERARCHICAL CLASSIFICATION.” In Proceedings of Machine Learning Research, 232:162–83, 2023.
Linderman R, Zhang J, Inkawhich N, Li H, Chen Y. FINE-GRAIN INFERENCE ON OUT-OF-DISTRIBUTION DATA WITH HIERARCHICAL CLASSIFICATION. In: Proceedings of Machine Learning Research. 2023. p. 162–83.
Linderman, R., et al. “FINE-GRAIN INFERENCE ON OUT-OF-DISTRIBUTION DATA WITH HIERARCHICAL CLASSIFICATION.” Proceedings of Machine Learning Research, vol. 232, 2023, pp. 162–83.
Linderman R, Zhang J, Inkawhich N, Li H, Chen Y. FINE-GRAIN INFERENCE ON OUT-OF-DISTRIBUTION DATA WITH HIERARCHICAL CLASSIFICATION. Proceedings of Machine Learning Research. 2023. p. 162–183.

Published In

Proceedings of Machine Learning Research

EISSN

2640-3498

Publication Date

January 1, 2023

Volume

232

Start / End Page

162 / 183