Research map / Label-efficient and robust learning / Recognition and long-tail
Learning Network Architecture for Open-Set Recognition
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 the searched OSR architecture and training pipeline instead of GCM-CF | OSR models · CIFAR10 | AUROC: 0.720 -> 0.843 | Helped |
| Use the searched OSR architecture and training pipeline instead of the strongest prior baseline | OSR models · SVHN | AUROC: 0.910 -> 0.949 | Helped |
| Use the searched OSR architecture and training pipeline instead of the strongest prior baseline | OSR models · C+50 | AUROC: 0.827 -> 0.871 | Helped |
| Use the searched OSR architecture and training pipeline instead of the strongest prior baseline | OSR models · C+10 | AUROC: 0.838 -> 0.840 | Helped |
| Use the searched OSR architecture and training pipeline instead of the strongest prior baseline | OSR models · MNIST | AUROC: 0.991 -> 0.961 | Hurt |
| Use the searched OSR architecture and training pipeline instead of GCM-CF | OSR models · CIFAR10 | macro F1 score: 72.63 -> 75.29 | Helped |
| Use the searched OSR architecture and training pipeline instead of GCM-CF | OSR models · MNIST | macro F1 score: 91.37 -> 92.04 | Helped |
| Add VAE contrastive loss during architecture search (ablation) | OSR-NAS · SVHN | macro F1 score: 81.76 -> 83.02; 1.26% increase | Helped |
| Add Pseudo Auxiliary Searching (ablation) | OSR-NAS · SVHN | macro F1 score: 79.72 -> 82.30 | Helped |
| Add branches 0 and 1 (ablation) | OSR-NAS · SVHN | macro F1 score: 83.02 -> 81.67 | Hurt |
Closest papers by meaning
- All Beings Are Equal in Open Set Recognition (AAAI 2024 · similarity 0.90)
- From Coarse to Fine-Grained Open-Set Recognition (CVPR 2024 · similarity 0.89)
- Unlocking Better Closed-Set Alignment Based on Neural Collapse for Open-Set Recognition (AAAI 2025 · similarity 0.87)
- Frequency Shuffling and Enhancement for Open Set Recognition (AAAI 2024 · similarity 0.87)
- Exploring Diverse Representations for Open Set Recognition (AAAI 2024 · similarity 0.86)
- Improving Open Set Recognition via Visual Prompts Distilled from Common-Sense Knowledge (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.