Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Latent Discriminant Deterministic Uncertainty
Gianni Franchi, Xuanlong Yu, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, David Filliat
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add entropy loss to uncertainty loss (ablation) | LDU · CIFAR-10 OOD vs SVHN | AUC: 0.8195 -> 0.8362 | Improved |
| add discriminative loss to uncertainty loss (ablation) | LDU · CIFAR-10 OOD vs SVHN | AUC: 0.8195 -> 0.8613 | Improved |
| add all three losses versus uncertainty loss alone (ablation) | LDU · CIFAR-10 OOD vs SVHN | AUC: 0.8195 -> 0.8721 | Improved |
| add entropy loss to uncertainty plus discriminative loss (ablation) | LDU · CIFAR-10 OOD vs SVHN | AUC: 0.8613 -> 0.8721 | Improved |
| add entropy loss to uncertainty loss (ablation) | LDU · CIFAR-10 | ECE: 0.5256 -> 0.5386 | Hurt |
| increase prototypes from 16 to 128 (ablation) | LDU · CIFAR-10 OOD vs SVHN | AUC: 0.8479 -> 0.8721 | Mixed |
| raise lambda from 0.1 to 2.0 (ablation) | LDU · CIFAR-10 OOD vs SVHN | AUC: 0.8721 -> 0.8339 | Hurt |
| use LDU instead of baseline MCP | DNN · CIFAR-10 OOD vs SVHN | AUC: 0.8032 -> 0.8721 | Improved |
| use LDU instead of baseline MCP | Deeplab v3+ · MUAD OOD set | AUPR: 0.2604 -> 0.4418 | Improved |
| use LDU instead of Deep Ensembles | Deeplab v3+ · MUAD OOD set | AUROC: 0.871 -> 0.8816 | Improved |
| use LDU instead of Deep Ensembles | Deeplab v3+ · Cityscapes | mIoU: 77.23% -> 76.62% | No clear effect |
| use LDU instead of Deep Ensembles | Deeplab v3+ · semantic segmentation inference time | runtime ms: 56 -> 14 | Improved |
Closest papers by meaning
- Deep Deterministic Uncertainty: A New Simple Baseline (CVPR 2023 · similarity 0.91)
- On the Practicality of Deterministic Epistemic Uncertainty (ICML 2022 · similarity 0.91)
- Hyperdimensional Uncertainty Quantification for Multimodal Uncertainty Fusion in Autonomous Vehicles Perception (CVPR 2025 · similarity 0.87)
- Predictive Uncertainty Quantification for Bird's Eye View Segmentation: A Benchmark and Novel Loss Function (ICLR 2025 · similarity 0.87)
- UncertainSAM: Fast and Efficient Uncertainty Quantification of the Segment Anything Model (ICML 2025 · similarity 0.86)
- Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models (CVPR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
