AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

MetaKernel: Learning Variational Random Features With Limited Labels

Yingjun Du, Haoliang Sun, Xiantong Zhen, Jun Xu, Yilong Yin, Ling Shao, Cees G. M. Snoek

TPAMI 2022 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Bayesian view of meta-learning · 16 citations (OpenAlex)

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 changedWhereMeasuredEffect
use random Fourier features instead of RBF kernel (ablation)MetaKernel · miniImageNet 5-way 1-shotaccuracy (%): 42.1 -> 52.8Improved
use random Fourier features instead of RBF kernel (ablation)MetaKernel · CIFAR-FS 5-way 5-shotaccuracy (%): 59.8 -> 74.7Improved
use variational RFFs instead of plain RFFs (ablation)MetaKernel · miniImageNet 5-way 1-shotaccuracy (%): 52.8 -> 51.3Hurt
use variational RFFs instead of plain RFFs (ablation)MetaKernel · miniImageNet 5-way 5-shotaccuracy (%): 65.4 -> 66.1No clear effect
use variational RFFs instead of plain RFFs (ablation)MetaKernel · CIFAR-FS 5-way 5-shotaccuracy (%): 74.7 -> 74.3No clear effect
add task context inference (LSTM) to variational RFFs (ablation)MetaKernel · miniImageNet 5-way 1-shotaccuracy (%): 51.3 -> 54.2Improved
add task context inference (LSTM) to variational RFFs (ablation)MetaKernel · CIFAR-FS 5-way 1-shotaccuracy (%): 61.1 -> 63.1Improved
add task context inference (LSTM) to variational RFFs (ablation)MetaKernel · CIFAR-FS 5-way 5-shotaccuracy (%): 74.3 -> 76.5Improved
add conditional normalizing flows to enrich random features (ablation)MetaKernel · miniImageNet 5-way 1-shotaccuracy (%): 54.2 -> 55.5Improved
add conditional normalizing flows to enrich random features (ablation)MetaKernel · CIFAR-FS 5-way 1-shotaccuracy (%): 63.1 -> 64.3Improved
add conditional normalizing flows to enrich random features (ablation)MetaKernel · miniImageNet 5-way 1-shot (pretrained WRN-28-10)accuracy (%): 63.80 -> 65.03Improved
MetaKernel vs MetaNorm in few-shot domain generalizationMetaKernel · DomainNet 5-wayaccuracy (%): 32.7 -> 34.7 (1-shot); 51.9 -> 53.7 (5-shot)Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy