Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection
This addresses the challenge of detecting outliers in data with semantic coherence, which is crucial for robust machine learning systems, though it appears incremental as it builds on existing SCOOD benchmarks.
The paper tackles the problem of semantically coherent out-of-distribution detection by proposing an uncertainty-aware optimal transport scheme, which improves OOD detection performance by margins of 27.69% and 34.4% on FPR@95 compared to state-of-the-art methods.
Semantically coherent out-of-distribution (SCOOD) detection aims to discern outliers from the intended data distribution with access to unlabeled extra set. The coexistence of in-distribution and out-of-distribution samples will exacerbate the model overfitting when no distinction is made. To address this problem, we propose a novel uncertainty-aware optimal transport scheme. Our scheme consists of an energy-based transport (ET) mechanism that estimates the fluctuating cost of uncertainty to promote the assignment of semantic-agnostic representation, and an inter-cluster extension strategy that enhances the discrimination of semantic property among different clusters by widening the corresponding margin distance. Furthermore, a T-energy score is presented to mitigate the magnitude gap between the parallel transport and classifier branches. Extensive experiments on two standard SCOOD benchmarks demonstrate the above-par OOD detection performance, outperforming the state-of-the-art methods by a margin of 27.69% and 34.4% on FPR@95, respectively.