Research map / Label-efficient and robust learning / OOD and anomaly detection
Image-based Outlier Synthesis With Training Data
Sudarshan Regmi
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 gradient to ID inputs instead of subtracting it for outlier synthesis (ablation) | ASCOOD · Car (fine-grained) | FPR@95: 60.20 -> 40.76 | Improved |
| add gradient (vs pixel shuffling) for outlier synthesis (ablation) | ASCOOD · Aircraft (fine-grained) | FPR@95: 47.98 -> 47.94 | No clear effect |
| use z-score instead of L2 normalization of features (ablation) | ASCOOD · Car (fine-grained) | FPR@95: 51.86 -> 40.76 | Improved |
| use z-score instead of L2 normalization (ablation) | ASCOOD · CIFAR-100 | FPR@95: 40.81 -> 29.90 | Improved |
| use KL-to-uniform loss instead of energy loss for outlier uncertainty (ablation) | ASCOOD · Aircraft (fine-grained) | FPR@95: 58.70 -> 47.94 | Improved |
| standardize features rather than raw features with KL loss (ablation) | ASCOOD · Aircraft (fine-grained) | FPR@95: 55.21 -> 47.94 | Improved |
| use i-ODIN (perturb only significant channels) instead of ODIN (ablation) | ODIN · CIFAR-10 vs CIFAR-100 | FPR@95: 77.00 -> 61.33 | Improved |
| use i-ODIN instead of ODIN on two-class benchmarks (ablation) | ODIN · Waterbirds and CelebA | FPR@95 | No clear effect |
| train with ASCOOD vs baseline | ResNet · ID accuracy | accuracy: 76.63 vs 77.25 (CIFAR-100) | No clear effect |
| ASCOOD vs external-data OE/MixOE | ASCOOD · Waterbirds (spurious) | FPR@95: 33.26 -> 11.37 | Improved |
Closest papers by meaning
- Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation (NeurIPS 2024 · similarity 0.91)
- Out-of-Distribution Detection with Prototypical Outlier Proxy (AAAI 2025 · similarity 0.91)
- Mining In-distribution Attributes in Outliers for Out-of-distribution Detection (AAAI 2025 · similarity 0.91)
- Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection (NeurIPS 2025 · similarity 0.90)
- EAT: Towards Long-Tailed Out-of-Distribution Detection (AAAI 2024 · similarity 0.90)
- Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning (AAAI 2024 · 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.
