Learning by Erasing: Conditional Entropy Based Transferable Out-of-Distribution Detection
DOI:
https://doi.org/10.1609/aaai.v38i6.28444Keywords:
CV: Interpretability, Explainability, and Transparency, CV: Adversarial Attacks & Robustness, CV: Low Level & Physics-based Vision, ML: Representation Learning, ML: Transfer, Domain Adaptation, Multi-Task Learning, ML: Unsupervised & Self-Supervised LearningAbstract
Detecting OOD inputs is crucial to deploy machine learning models to the real world safely. However, existing OOD detection methods require an in-distribution (ID) dataset to retrain the models. In this paper, we propose a Deep Generative Models (DGMs) based transferable OOD detection that does not require retraining on the new ID dataset. We first establish and substantiate two hypotheses on DGMs: DGMs exhibit a predisposition towards acquiring low-level features, in preference to semantic information; the lower bound of DGM's log-likelihoods is tied to the conditional entropy between the model input and target output. Drawing on the aforementioned hypotheses, we present an innovative image-erasing strategy, which is designed to create distinct conditional entropy distributions for each individual ID dataset. By training a DGM on a complex dataset with the proposed image-erasing strategy, the DGM could capture the discrepancy of conditional entropy distribution for varying ID datasets, without re-training. We validate the proposed method on the five datasets and show that, without retraining, our method achieves comparable performance to the state-of-the-art group-based OOD detection methods. The project codes will be open-sourced on our project website.Downloads
Published
2024-03-24
How to Cite
Xing, M., Feng, Z., Su, Y., & Oh, C. (2024). Learning by Erasing: Conditional Entropy Based Transferable Out-of-Distribution Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 6261-6269. https://doi.org/10.1609/aaai.v38i6.28444
Issue
Section
AAAI Technical Track on Computer Vision V