# CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveraging

arXiv: https://arxiv.org/abs/2503.00325 · HTML: https://mlsanity.com/paper/2503.00325/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 56 references that are in the map.
- First posted on arXiv 1 Mar 2025.

## Builds on (most cited first, 30 of 40)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [ReAct: Out-of-distribution Detection With Rectified Activations](https://mlsanity.com/paper/2111.12797/) (2021)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [Scaling Out-of-Distribution Detection for Real-World Settings](https://mlsanity.com/paper/1911.11132/) (2019)
- [ViM: Out-Of-Distribution with Virtual-logit Matching](https://mlsanity.com/paper/2203.10807/) (2022)
- [Open-Set Recognition: a Good Closed-Set Classifier is All You Need?](https://mlsanity.com/paper/2110.06207/) (2021)
- [Mitigating Neural Network Overconfidence with Logit Normalization](https://mlsanity.com/paper/2205.09310/) (2022)
- [MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space](https://mlsanity.com/paper/2105.01879/) (2021)
- [Extremely Simple Activation Shaping for Out-of-Distribution Detection](https://mlsanity.com/paper/2209.09858/) (2022)
- [OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection](https://mlsanity.com/paper/2306.09301/) (2023)
- [DICE: Leveraging Sparsification for Out-of-Distribution Detection](https://mlsanity.com/paper/2111.09805/) (2021)
- [TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Tracking](https://mlsanity.com/paper/1504.06755/) (2015)
- [In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation](https://mlsanity.com/paper/2306.00826/) (2023)
- [How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?](https://mlsanity.com/paper/2203.04450/) (2022)
- [Deep Learning for Hyperspectral Image Classification: An Overview](https://mlsanity.com/paper/1910.12861/) (2019)
- [Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement](https://mlsanity.com/paper/2310.00227/) (2023)

## Built on by (most cited first, 9 of 9)

- [GEPC: Group-Equivariant Posterior Consistency for Out-of-Distribution Detection in Diffusion Models](https://mlsanity.com/paper/2602.00191/) (2026)
- [GAFD-CC: Global-Aware Feature Decoupling with Confidence Calibration for OOD Detection](https://mlsanity.com/paper/2511.02335/) (2025)
- [Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection](https://mlsanity.com/paper/2602.01039/) (2026)
- [DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection](https://mlsanity.com/paper/2604.23729/) (2026)
- [Evidence-Guided Unknown Rejection for High-Confidence Near-Known Unknowns](https://mlsanity.com/paper/2605.17818/) (2026)
- [Modality-Aware Out-of-Distribution Detection for Multi-Modal Action Recognition](https://mlsanity.com/paper/2606.24404/) (2026)
- [Training-Free Out-of-Distribution Detection for Pathology Whole-Slide Images](https://mlsanity.com/paper/2608.01407/) (2026)
- [CHILD: Human-in-the-Loop OOD Detection for Safe Clinical Deployment](https://mlsanity.com/paper/2609.07188/) (2026)
- [CUBE: Class-conditioned Unknown Boundary Evidence for Open-Set Insect Species Recognition](https://mlsanity.com/paper/2610.13610/) (2026)

## Abstract (arXiv)

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 Class-Aware Relative Feature-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 Class-Aware Decoupled Relative Feature-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.