Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Vibration-Based Uncertainty Estimation for Learning from Limited Supervision
Hengtong Hu, Lingxi Xie, Xinyue Huo, Richang Hong, Qi Tian
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 label flipping sequence to the probability vibration measure (ablation) | vibration uncertainty · Active learning CIFAR10 iter 1 | test error (%): 35.37 -> 27.33 | Improved |
| add label flipping sequence to the probability vibration measure (ablation) | vibration uncertainty · Active learning CIFAR100 iter 1 | test error (%): 45.64 -> 43.99 | Improved |
| add class weights for pseudo label selection (ablation) | vibration pseudo label mining with Mean Teacher · Mini-ImageNet SSL (4000 and 10000 labels) | accuracy: 0.86% and 0.85% gains | Improved |
| add vibration-based pseudo labels | Mean Teacher (RA) · CIFAR100 SSL (4000 labels) | test error (%): 43.86 -> 36.86 | Improved |
| add vibration-based pseudo labels | FixMatch (RA) · CIFAR10 SSL (250 labels) | test error (%): 6.16 -> 6.06 | Improved |
| add vibration-based pseudo labels | FixMatch (RA) · CIFAR100 SSL (4000 labels) | test error (%): 31.22 -> 30.40 | Improved |
| replace MC Dropout uncertainty with vibration fused | active learning on Mean Teacher · CIFAR10 iter 1 | test error (%): 33.27 -> 27.33 | Improved |
| replace K-center selection with vibration fused | active learning on Mean Teacher · CIFAR10 iter 1 | test error (%): 35.53 -> 27.33 | Improved |
| start the sampled sequence at a later epoch instead of early epochs (ablation) | vibration uncertainty · Active learning CIFAR10 and CIFAR100 iter 1 | test error | Improved |
| increase balance coefficient mu above 0.1 (ablation) | vibration uncertainty · Active learning CIFAR10 and CIFAR100 iter 1 | test error | Hurt |
| add vibration-based noisy sample handling | Mean Teacher · CIFAR10 with 0.2 label noise | test error (%): 13.82 -> 10.06 | Improved |
| add vibration-based noisy sample handling | Mean Teacher · CIFAR10 with 0.4 label noise | test error (%): 18.19 -> 12.77 | Improved |
Closest papers by meaning
- Sparse Uncertainty Representation in Deep Learning with Inducing Weights (NeurIPS 2021 · similarity 0.85)
- Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness (NeurIPS 2020 · similarity 0.85)
- Post-hoc Uncertainty Learning Using a Dirichlet Meta-Model (AAAI 2023 · similarity 0.85)
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (NeurIPS 2017 · similarity 0.85)
- Uncertainty Quantification with the Empirical Neural Tangent Kernel (NeurIPS 2025 · similarity 0.85)
- Deep Active Learning with Noise Stability (AAAI 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.
