Research map / Label-efficient and robust learning / Recognition and long-tail
Operational Open-Set Recognition and PostMax Refinement
Steve Cruz, Ryan Rabinowitz, Manuel Günther, Terrance E. Boult
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 |
|---|---|---|---|
| normalize maximum logit by deep feature magnitude and map with a generalized Pareto distribution (PostMax) instead of raw MSP or MaxLogit | Hiera-H on ILSVRC2012 · OpenImage-O | OOSA: 0.814 -> 0.864 vs MSP | Improved |
| PostMax versus MSP on a hard fine-grained unknown set (ablation) | Hiera-H and ConvNeXtV2-H · 21K-P Hard test, 21K-P Easy surrogate | OOSA: 0.634 vs MSP 0.673 (Hiera-H) | Hurt |
| swap validation knowns to ILSVRC2012 val and unknown surrogate to 21K-P Easy (ablation) | PostMax · iNaturalist, OpenImage-O | OOSA: 0.825 -> 0.863 (iNaturalist, Hiera-H) | No clear effect |
| operate on ConvNeXtV2-H instead of Hiera-H (ablation) | PostMax · iNaturalist | OOSA: 0.825 -> 0.812 | No clear effect |
| divide logits by deep feature magnitude, since unknowns have larger feature norms | PostMax · ViT-H feature analysis on class 990 | mean L2 norm of features: known 3.48 vs unknown 5.50 mean L2 norm | Improved |
| use PostMax with GPD probabilities versus NNGuide and SCALE OOD baselines | Hiera-H · 21K-P Easy | OOSA: 0.818 vs NNGuide 0.744 and SCALE 0.568 | Improved |
Closest papers by meaning
- Learning Network Architecture for Open-Set Recognition (AAAI 2022 · similarity 0.90)
- Open-Set Recognition: A Good Closed-Set Classifier is All You Need (ICLR 2022 · similarity 0.90)
- GHOST: Gaussian Hypothesis Open-Set Technique (AAAI 2025 · similarity 0.87)
- From Coarse to Fine-Grained Open-Set Recognition (CVPR 2024 · similarity 0.87)
- All Beings Are Equal in Open Set Recognition (AAAI 2024 · similarity 0.86)
- Frequency Shuffling and Enhancement for Open Set Recognition (AAAI 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.
