Research map / Probabilistic and scientific modeling / Variational and generative sampling
Understanding Failures in Out-of-Distribution Detection with Deep 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 |
|---|---|---|---|
| Replace MLE training with the negative training objective, which lowers likelihood on MNIST while maximizing it on Fashion-MNIST | PixelCNN++ · Fashion-MNIST vs MNIST | OOD AUC: 0.097 ± 0.004 -> 1.000 ± 0.000 | Helped |
| Replace MLE training with the negative training objective | PixelCNN++ · Fashion-MNIST | held-out log likelihood: -1550 ± 6 -> -1562 ± 7 | Hurt |
| Train a separate Glow model for 50 epochs on samples from the pretrained Glow model | Glow OOD detection using likelihood · Glow-model samples vs CelebA | OOD detection performance | Helped |
Closest papers by meaning
- Understanding Likelihood of Normalizing Flow and Image Complexity through the Lens of Out-of-Distribution Detection (AAAI 2024 · similarity 0.92)
- Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution (ICML 2025 · similarity 0.91)
- A Geometric Explanation of the Likelihood OOD Detection Paradox (ICML 2024 · similarity 0.91)
- Out-of-Distribution Detection with Prototypical Outlier Proxy (AAAI 2025 · similarity 0.90)
- Image Background Serves as Good Proxy for Out-of-distribution Data (ICLR 2024 · similarity 0.90)
- Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection (NeurIPS 2025 · similarity 0.90)
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.