Research map / Label-efficient and robust learning / Test-time adaptation
No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks
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 |
|---|---|---|---|
| Apply Conditional Risk Minimization as a post-hoc decision rule to cross-entropy likelihoods | Cross-Entropy classifier · tieredImageNet-H and iNaturalist-H | Hierarchical distance@k | Helped |
| Apply Conditional Risk Minimization as a post-hoc decision rule to cross-entropy likelihoods | Cross-Entropy classifier · tieredImageNet-H and iNaturalist-H | top-1 accuracy | No clear effect |
| Increase Soft-labels Beta from 30 to 50 (ablation) | Soft-labels · iNaturalist19 | Hier. Distance@5: 1.554$\pm$0.006 -> 1.879$\pm$ 0.003 | Hurt |
| Increase Soft-labels Beta from 30 to 75 (ablation) | Soft-labels · iNaturalist19 | Hier. Distance@5: 1.554$\pm$0.006 -> 1.916$\pm$0.005 | Hurt |
| Increase Soft-labels Beta from 30 to 100 (ablation) | Soft-labels · iNaturalist19 | Hier. Distance@5: 1.554$\pm$0.006 -> 1.926$\pm$0.005 | Hurt |
| Increase Soft-labels Beta from 30 to 200 (ablation) | Soft-labels · iNaturalist19 | Hier. Distance@5: 1.554$\pm$0.006 -> 1.924$\pm$0.005 | Hurt |
Closest papers by meaning
- Making Better Mistakes: Leveraging Class Hierarchies With Deep Networks (CVPR 2020 · similarity 0.88)
- Test-Time Amendment with a Coarse Classifier for Fine-Grained Classification (NeurIPS 2023 · similarity 0.86)
- To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical Classifiers (ICML 2025 · similarity 0.85)
- Hierarchical Selective Classification (NeurIPS 2024 · similarity 0.84)
- Automated Classification of Model Errors on ImageNet (NeurIPS 2023 · similarity 0.84)
- Error Correction Output Codes for Robust Neural Networks against Weight-errors: A Neural Tangent Kernel Point of View (NeurIPS 2024 · similarity 0.82)
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.