Research map / Label-efficient and robust learning / OOD and anomaly detection
Towards In-Distribution Compatible Out-of-Distribution Detection
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 ICE instead of Energy | WideResNet, from-scratch · CIFAR-10 in-distribution, CIFAR-100 OOD | FPR95: 26.15 -> 22.36 | Helped |
| Use ICE instead of Energy | WideResNet, from-scratch · CIFAR-10 | in-distribution accuracy: 94.13 -> 96.38 | Helped |
| Use ICE instead of Energy | WideResNet(G) · CIFAR-10, average across OOD sets | FPR95: 4.01 -> 3.33 | Helped |
| Replace the linear classifier with the Gaussian-like WideResNet(G) head (ablation) | Energy · CIFAR-10, average across OOD sets | FPR95: 4.12 -> 4.01 | Helped |
| Replace the linear classifier with the Gaussian-like WideResNet(G) head (ablation) | Energy · CIFAR-10 | in-distribution accuracy: 94.13 -> 93.95 | Hurt |
| Use Sigmoid Binary Cross-Entropy loss instead of the ICE loss (ablation) | WideResNet · CIFAR-10, average across OOD sets | FPR95: 4.48 vs 3.33 | Mixed |
| Use Sigmoid Binary Cross-Entropy loss instead of the ICE loss (ablation) | WideResNet · CIFAR-10 | in-distribution accuracy: 95.81 vs 96.38 | Hurt |
| Add the in-distribution likelihood loss Lice-id (ablation) | ICE · CIFAR-10, average across OOD sets | AUROC: 74.03 -> 99.16 | Helped |
| Add the in-distribution likelihood loss Lice-id (ablation) | ICE · CIFAR-10 | in-distribution accuracy: 90.44 -> 96.38 | Helped |
Closest papers by meaning
- Out-of-Distribution Detection with Prototypical Outlier Proxy (AAAI 2025 · similarity 0.88)
- DOS: Diverse Outlier Sampling for Out-of-Distribution Detection (ICLR 2024 · similarity 0.87)
- Mining In-distribution Attributes in Outliers for Out-of-distribution Detection (AAAI 2025 · similarity 0.87)
- ALTBI: Constructing Improved Outlier Detection Models via Optimization of Inlier-Memorization Effect (AAAI 2025 · similarity 0.86)
- Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution (ICML 2025 · similarity 0.86)
- Out-Of-Distribution Detection with Diversification (Provably) (NeurIPS 2024 · 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.