Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Learning to Learn Dense Gaussian Processes for Few-Shot Learning
Ze Wang, Zichen Miao, Xiantong Zhen, Qiang Qiu
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 |
|---|---|---|---|
| increase number of dense inducing variables m from 8 up to 1024 (ablation) | Dense GP · CUB 5-way 1-shot and 5-shot | accuracy | Improved |
| more inner-loop adaptation steps beyond 5 (ablation) | Dense GP · CUB 5-way 5-shot | accuracy | No clear effect |
| large inner-loop learning rate with more than 1 step (ablation) | Dense GP · CUB 5-way 5-shot | accuracy | Hurt |
| dense GP with meta-learned inducing variables vs prior GP methods (DKT) | few-shot GP · CUB 5-way 1-shot Conv-4 | accuracy: 62.96 -> 69.18 | Improved |
| dense GP vs best baseline VSM | miniImageNet 5-way 5-shot · miniImageNet | accuracy: 68.01 -> 72.64 | Improved |
Closest papers by meaning
- Dense Gaussian Processes for Few-Shot Segmentation (ECCV 2022 · similarity 0.87)
- Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertainties (NeurIPS 2020 · similarity 0.87)
- Convolutional Gaussian Processes (NeurIPS 2017 · similarity 0.87)
- Generic Inference in Latent Gaussian Process Models (JMLR 2019 · similarity 0.86)
- Scalable Training of Inference Networks for Gaussian-Process Models (ICML 2019 · similarity 0.86)
- Accelerating Convergence in Bayesian Few-Shot Classification (ICML 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.
