Research map / Label-efficient and robust learning / Recognition and long-tail
Conditional Gaussian Distribution Learning 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 |
|---|---|---|---|
| Add the probabilistic ladder architecture to CVAE (ablation) | CVAE open-set classifier · CIFAR-100 ablation (varying Openness) | F1-score | Helped |
| Add conditional Gaussian distributions for unknown detection to CVAE without ladder architecture (ablation) | CVAE · CIFAR-100 ablation (varying Openness) | F1-score | No clear effect |
| Add the probabilistic ladder architecture to CGD-based unknown detection (ablation) | CVAE+CGD · CIFAR-100 ablation (varying Openness) | F1-score | Helped |
| Use reconstruction errors instead of CGD for unknown detection (ablation) | LCVAE · CIFAR-100 ablation (varying Openness) | F1-score | Hurt |
| Add reconstruction errors to CGD-based unknown detection (ablation) | LCVAE+CGD · CIFAR-100 ablation (varying Openness) | F1-score | Helped |
| Replace the plain CNN with CGDL | Closed-set classifier · MNIST closed-set test | accuracy: 0.997 -> 0.996 | Hurt |
| Replace the plain CNN with CGDL | Closed-set classifier · SVHN closed-set test | accuracy: 0.944 -> 0.942 | Hurt |
| Replace the plain CNN with CGDL | Closed-set classifier · CIFAR-10 closed-set test | accuracy: 0.912 -> 0.912 | No clear effect |
| Use CGDL instead of the strongest listed baseline | Open-set recognition method · CIFAR-10 | macro-averaged F1-score: 0.700 ± 0.024 -> 0.655 ± 0.023 | Hurt |
Closest papers by meaning
- Open-Set Recognition with Gaussian Mixture Variational Autoencoders (AAAI 2021 · similarity 0.88)
- C2AE: Class Conditioned Auto-Encoder for Open-Set Recognition (CVPR 2019 · similarity 0.88)
- Generative-Discriminative Feature Representations for Open-Set Recognition (CVPR 2020 · similarity 0.87)
- GHOST: Gaussian Hypothesis Open-Set Technique (AAAI 2025 · similarity 0.86)
- Frequency Shuffling and Enhancement for Open Set Recognition (AAAI 2024 · similarity 0.84)
- Exploring Diverse Representations for Open Set Recognition (AAAI 2024 · similarity 0.83)
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.