Research map / Label-efficient and robust learning / Recognition and long-tail
C2AE: Class Conditioned Auto-Encoder for Open-Set Recognition
Check 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 class-conditioned reconstruction errors with the proposed method instead of OSRCI scores | Open-set identification · MNIST | AUROC: 0.988 -> 0.989 | Helped |
| Use class-conditioned reconstruction errors with the proposed method instead of OSRCI scores | Open-set identification · SVHN | AUROC: 0.910 -> 0.922 | Helped |
| Use class-conditioned reconstruction errors with the proposed method instead of OSRCI scores | Open-set identification · CIFAR10 | AUROC: 0.699 -> 0.895 | Helped |
| Use class-conditioned reconstruction errors with the proposed method instead of OSRCI scores | Open-set identification · CIFAR+10 | AUROC: 0.838 -> 0.955 | Helped |
| Use class-conditioned reconstruction errors with the proposed method instead of OSRCI scores | Open-set identification · CIFAR+50 | AUROC: 0.827 -> 0.937 | Helped |
| Use class-conditioned reconstruction errors with the proposed method instead of OSRCI scores | Open-set identification · TinyImageNet | AUROC: 0.586 -> 0.748 | Helped |
| Add match reconstruction loss to closed-set classification (ablation) | CLS open-set recognition on LFW · LFW | F-measure | Mixed |
| Add non-match reconstruction loss (ablation) | CLS+DEC open-set recognition on LFW · LFW | F-measure | Helped |
| Fit EVT models to reconstruction errors instead of thresholding raw reconstruction scores (ablation) | Naive open-set recognition on LFW · LFW | F-measure | Helped |
| Set the unknown-class prior to 0.5 times openness rather than fixing it at 0.5 (ablation) | Proposed method on LFW · LFW | F-measure | Helped |
Closest papers by meaning
- Generative-Discriminative Feature Representations for Open-Set Recognition (CVPR 2020 · similarity 0.90)
- All Beings Are Equal in Open Set Recognition (AAAI 2024 · similarity 0.86)
- Unlocking the Power of Open Set: A New Perspective for Open-Set Noisy Label Learning (AAAI 2024 · similarity 0.85)
- Unlocking Better Closed-Set Alignment Based on Neural Collapse for Open-Set Recognition (AAAI 2025 · similarity 0.85)
- Robust Visual Recognition with Class-Imbalanced Open-World Noisy Data (AAAI 2024 · similarity 0.85)
- From Coarse to Fine-Grained Open-Set Recognition (CVPR 2024 · similarity 0.84)
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.