Papers › Deep Hybrid Models for Out-of-Distribution Detection
Deep Hybrid Models for Out-of-Distribution Detection
Senqi Cao, Zhongfei Zhang
We propose a principled and practical method for out-of-distribution (OoD) detection with deep hybrid models (DHMs), which model the joint density p(x,y) of features and labels with a single forward pass. By factorizing the joint density p(x,y) into three sources of uncertainty, we show that our approach has the ability to identify samples semantically different from the training data. To ensure computational scalability, we add a weight normalization step during training, which enables us to plug in state-of-the-art (SoTA) deep neural network (DNN) architectures for approximately modeling and inferring expressive probability distributions. Our method provides an efficient, general, and flexible framework for predictive uncertainty estimation with promising results and theoretical support. To our knowledge, this is the first work to reach 100% in OoD detection tasks on both vision and language datasets, especially on notably difficult dataset pairs such as CIFAR-10 vs. SVHN and CIFAR-100 vs. CIFAR-10. This work is a step towards enabling DNNs in real-world deployment for safety-critical applications.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Out-of-Distribution Detection | CIFAR-10 | DHM | AUROC | 100 | #1 of 10 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-10 | DHM | FPR95 | 0 | #1 of 10 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-10 vs CIFAR-100 | DHM | AUPR | 100 | #1 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-10 vs CIFAR-100 | DHM | AUROC | 100 | #1 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-100 vs CIFAR-10 | DHM | AUPR | 100 | #1 of 14 | Archive leaderboard | report |
| Out-of-Distribution Detection | CIFAR-100 vs CIFAR-10 | DHM | AUROC | 100 | #1 of 14 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections