Research map / Probabilistic and scientific modeling / Variational and generative sampling
Amortized Variational Inference for Partial-Label Learning: A Probabilistic Approach to Label Disambiguation
Tobias Fuchs, Nadja Klein
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 |
|---|---|---|---|
| use Markov-equivalent factorization P(Y)P(X|Y)P(S|X,Y) with CVAE generative model and prior instead of discriminative P(Y|X) (ablation) | ViPll · bird-song | accuracy: 72.25 -> 76.15 | Improved |
| use Markov-equivalent factorization P(Y)P(X|Y)P(S|X,Y) with CVAE generative model and prior instead of discriminative P(Y|X) (ablation) | ViPll · lost | accuracy: 77.00 -> 78.52 | No clear effect |
| use Markov-equivalent factorization P(Y)P(X|Y)P(S|X,Y) with CVAE generative model and prior instead of discriminative P(Y|X) (ablation) | ViPll · mir-flickr | accuracy: 65.25 -> 68.49 | No clear effect |
| use Markov-equivalent factorization P(Y)P(X|Y)P(S|X,Y) with CVAE generative model and prior instead of discriminative P(Y|X) (ablation) | ViPll · msrc-v2 | accuracy: 53.41 -> 60.24 | Improved |
| use Markov-equivalent factorization P(Y)P(X|Y)P(S|X,Y) with CVAE generative model and prior instead of discriminative P(Y|X) (ablation) | ViPll · yahoo-news | accuracy: 49.41 -> 63.99 | Improved |
| use Markov-equivalent factorization P(Y)P(X|Y)P(S|X,Y) with CVAE generative model and prior instead of discriminative P(Y|X) (ablation) | ViPll · mnist | accuracy: 52.93 -> 80.81 | Improved |
| use Markov-equivalent factorization P(Y)P(X|Y)P(S|X,Y) with CVAE generative model and prior instead of discriminative P(Y|X) (ablation) | ViPll · kmnist | accuracy: 40.41 -> 58.78 | Improved |
| use Markov-equivalent factorization P(Y)P(X|Y)P(S|X,Y) with CVAE generative model and prior instead of discriminative P(Y|X) (ablation) | ViPll · fmnist | accuracy: 67.36 -> 74.87 | Improved |
| use Markov-equivalent factorization P(Y)P(X|Y)P(S|X,Y) with CVAE generative model and prior instead of discriminative P(Y|X) (ablation) | ViPll · cifar10 | accuracy: 88.43 -> 96.64 | Improved |
| use Markov-equivalent factorization P(Y)P(X|Y)P(S|X,Y) with CVAE generative model and prior instead of discriminative P(Y|X) (ablation) | ViPll · cifar100 | accuracy: 45.74 -> 77.76 | Improved |
Closest papers by meaning
- Partial Multi-Label Learning with Probabilistic Graphical Disambiguation (NeurIPS 2023 · similarity 0.91)
- Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning (AAAI 2024 · similarity 0.89)
- Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning (AAAI 2024 · similarity 0.88)
- Conformal Prediction for Partial Label Learning (AAAI 2025 · similarity 0.88)
- Realistic Evaluation of Deep Partial-Label Learning Algorithms (ICLR 2025 · similarity 0.88)
- Partial Label Causal Representation Learning for Instance-Dependent Supervision and Domain Generalization (AAAI 2025 · similarity 0.88)
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.
