Research map / Label-efficient and robust learning / Recognition and long-tail
Set-valued Classification with Out-of-distribution Detection for Many Classes
Zhou Wang, Xingye Qiao
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 kernel feature selection (GPSKFS) to GPS (ablation) | GPS · Example 2 (simulation) | efficiency (%): 42 -> 84.2 | Improved |
| add kernel feature selection (GPSKFS) to GPS (ablation) | GPS · Example 1 (simulation) | efficiency (%): 90.8 -> 90.6 | No clear effect |
| add kernel feature selection (GPSKFS) to GPS (ablation) | GPS · Zipcode | OOD detection rate (%): 66.2 -> 73 | Improved |
| add kernel feature selection (GPSKFS) to GPS (ablation) | GPS · Phoneme | OOD detection rate (%): 98.6 -> 98.5 | No clear effect |
| add kernel feature selection (GPSKFS) to GPS under label shift (ablation) | GPS · Example 2 with label shift | efficiency (%): 59 -> 84.3 | Improved |
| increase proportion of OOD points in test data from 20% to 80% | GPS · Zipcode | OOD detection rate (%): 33.8 -> 68.7 | Improved |
| increase proportion of OOD points in test data from 20% to 80% | GPS · Zipcode | efficiency (%): 95.1 -> 90.5 | Hurt |
| increase proportion of OOD points in test data from 20% to 80% | GPS · Phoneme | efficiency (%): 84.3 -> 80.2 | Hurt |
| use neural embeddings from EOS (Hybrid GPS) instead of raw features | GPS · Cifar10 | OOD detection rate (%): 22.1 -> 95.3 | Improved |
| use neural embeddings from EOS (Hybrid GPS) instead of raw features | GPS · Cifar10 | efficiency (%): 14.5 -> 85.9 | Improved |
| use EBL embeddings (Hybrid GPS) instead of raw features | GPS · Cifar10 | OOD detection rate (%): 22.1 -> 52.7 | Improved |
| replace single-label EOS with set-valued Hybrid GPS | EOS · Cifar10 | efficiency (%): 100 -> 85.9 | Hurt |
Closest papers by meaning
- Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View (NeurIPS 2020 · similarity 0.84)
- KS(conf): A Light-Weight Test if a Multiclass Classifier Operates Outside of Its Specifications (IJCV 2019 · similarity 0.83)
- Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks (IJCV 2024 · similarity 0.83)
- Open-Set Recognition: A Good Closed-Set Classifier is All You Need (ICLR 2022 · similarity 0.83)
- EAT: Towards Long-Tailed Out-of-Distribution Detection (AAAI 2024 · similarity 0.81)
- Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning (AAAI 2024 · similarity 0.81)
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.
