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.
@article{arxiv.2303.10449,
title = {Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection},
author = {Fan Lu and Kai Zhu and Wei Zhai and Kecheng Zheng and Yang Cao},
journal= {arXiv preprint arXiv:2303.10449},
year = {2023}
}