Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Uncertainty-Aware Deep Classifiers Using Generative Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use GEN's predictive entropy to score out-of-distribution samples instead of the Calibrated method | LeNet-5 on MNIST · MNIST (first five vs last five categories) | AUC: 0.966 -> 0.965 | Hurt |
| Use GEN's predictive entropy to score out-of-distribution samples | LeNet-5 · CIFAR10 (first five vs last five categories) | AUC: 0.775 | Helped |
| Use GEN instead of Bayesian neural network approaches for uncertainty estimation | LeNet-5 · MNIST and CIFAR10 out-of-distribution samples | predictive uncertainty | Helped |
| Use GEN instead of standard networks or Bayesian neural networks | LeNet-5 · MNIST misclassified in-distribution samples | predictive uncertainty | Helped |
| Use GEN instead of other evaluated models for FGSM adversarial examples | LeNet-5 · MNIST and CIFAR10 | predictive uncertainty | Helped |
Closest papers by meaning
- Adaptive Uncertainty Estimation via High-Dimensional Testing on Latent Representations (NeurIPS 2023 · similarity 0.90)
- Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers (ICLR 2019 · similarity 0.89)
- UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs (NeurIPS 2022 · similarity 0.89)
- SURE: SUrvey REcipes for building reliable and robust deep networks (CVPR 2024 · similarity 0.88)
- Uncertainty Estimation by Flexible Evidential Deep Learning (NeurIPS 2025 · similarity 0.87)
- Random-Set Neural Networks (ICLR 2025 · similarity 0.86)
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.