Abstract: Deep neural networks (DNNs) have been widely criticized for their overconfidence when dealing with out-of-distribution (OOD) samples, highlighting the critical need for effective OOD detection to ensure the safe deployment of DNNs in real-world settings. Existing post-hoc OOD detection methods primarily enhance the discriminative power of logit-based approaches by reshaping sample features, yet they often neglect critical information inherent in the features themselves. In this paper, we propose the $\underline{C}lass$-$\underline{A}ware$ $\underline{Re}lative$ $\underline{F}eature$-based method (CARef), which utilizes the error between a sample’s feature and its class-aware average feature as a discriminative criterion. To further refine this approach, we introduce the $\underline{C}lass$-$\underline{A}ware$ $\underline{D}ecoupled$ $\underline{Re}lative$ $\underline{F}eature$-based method (CADRef), which decouples sample features based on the alignment of signs between the relative feature and corresponding model weights, enhancing the discriminative capabilities of CARef.Extensive experimental results across multiple datasets and models demonstrate that both proposed methods exhibit effectiveness and robustness in OOD detection compared to state-of-the-art methods. Specifically, our two methods outperform the best baseline by 2.82\% and 3.27\% in AUROC, with improvements of 4.03\% and 6.32\% in FPR95, respectively.